Tag: credit risk models

For lenders, first payment default (FPD) is more than just financial jargon; it's a crucial metric in assessing credit risk. This blog post will walk you through the essentials of FPD,  from defining the term to exploring how you can prevent and mitigate its potential impact. Understanding first payment default FPD occurs when a consumer fails to make their initial payment on a loan or credit agreement, which is often perceived as an early signal of a potential cascade of risky behavior. Recognizing FPD is the starting point for lenders to address potential issues with new borrowers before they escalate. One important aspect to grasp is the timeline of FPD. It’s not just about missing the first payment; it's about "early" missing. The timing of defaults is often critical in assessing the overall risk profile of a borrower or group of borrowers. The earlier a borrower starts to miss payments, the riskier they tend to be. Examining the causes of FPD The roots of FPD are diverse and can be classified into two broad categories: External factors: These include sudden financial crises, changes in employment status, or unforeseen expenses. Such factors are often beyond the borrower's immediate control. Internal factors: This category covers more deliberate or chronic financial habits, such as overspending, lack of savings, or overleveraging on credit. It's often indicative of longer-term financial instability. Understanding the causes of early payment default is the first step in effective risk management and customer engagement strategies. Implications of FPD for lenders FPD doesn't just signal immediate financial loss for lenders in terms of the missed installment. It sets off a cascade of consequences that affect the bottom line and the reputation of the institution. Financial loss. Lenders incur direct financial losses when a payment is missed, but the implications go beyond the missed payment amount. There are immediate costs associated with servicing, collections, and customer support. In the longer term, repeated defaults can lead to write-offs, impacting the institution's profitability and regulatory standing. Regulatory scrutiny. Repeated instances of FPD can also draw the attention of regulators, leading to scrutiny and potentially increased compliance costs. Mitigating first payment default Mitigating FPD requires a multifaceted approach that blends data, advanced analytics, customer engagement, and agile risk management. Lenders need to adopt strategies that can detect early signs of potential FPD and intervene preemptively. Data-driven decision-making. Leveraging advanced analytics and credit risk modeling is crucial. By incorporating transactional and behavioral data, lenders can make more accurate assessments of a borrower's risk profile. Utilizing predictive models can help forecast which borrowers are likely to default on their first payment, allowing for early intervention. Proactive customer engagement. Initiatives that revolve around education, personalized financial planning advice, and flexible payment arrangements can help borrowers who might be at risk of FPD. Proactive outreach can engage customers before a default occurs, turning a potential negative event into a positive experience. Agile risk management. Risk management strategies should be dynamic and responsive to changing market and customer conditions. Regularly reviewing and updating underwriting criteria, credit policies, and risk assessment tools ensures that lenders are prepared to tackle FPD challenges as they arise. Using FPD as a customer management tool Lastly, and perhaps most importantly, lenders can use FPD as a tool to foster better customer management. Every FPD is a data point that can provide insights into customer behavior and financial trends. By studying the causes and outcomes of FPD, lenders can refine their risk mitigation tools and improve their customer service offerings. Building trust through handling defaults. How lenders handle defaults, specifically the first ones, can significantly impact customer trust. Transparent communication, fair and considerate policies, and supportive customer service can make a difference in retaining customers and improving the lender's brand image. Leveraging data for personalization. The increasing availability of data means lenders can offer more personalized services. By segmenting customers based on payment behavior and response to early interventions, lenders can tailor offerings that meet the specific financial needs and challenges of individual borrowers. How Experian® can help First payment default is a critical aspect of credit risk management that requires attention and proactive strategies. By understanding the causes, implications, and mitigation strategies associated with FPD, financial institutions can not only avoid potential losses but also build stronger, more enduring relationships with their customers. Learn more about Experian’s credit risk modeling solutions. Learn more This article includes content created by an AI language model and is intended to provide general information.

Today's lenders use expanded data sources and advanced analytics to predict credit risk more accurately and optimize their lending and operations. The result may be a win-win for lenders and customers. What is credit risk? Credit risk is the possibility that a borrower will not repay a debt as agreed. Credit risk management encompasses the policies, tools and systems that lenders use to understand this risk. These can be important throughout the customer lifecycle, from marketing and sending preapproved offers to underwriting and portfolio management. Poor risk management can lead to unnecessary losses and missed opportunities, especially because risk departments need to manage risk with their organization's budgetary, technical and regulatory constraints in mind. How is it assessed?  Credit risk is often assessed with credit risk analytics — statistical modeling that predicts the risk involved with credit lending. Lenders may create and use credit risk models to help drive decisions. Additionally (or alternatively), they rely on generic or custom credit risk scores: Generic scores: Analytics companies create predictive models that rank order consumers based on the likelihood that a person will fall 90 or more days past due on any credit obligation in the next 24 months. Lenders can purchase these risk scores to help them evaluate risk. Custom scores: Custom credit risk modeling solutions help organizations tailor risk scores for particular products, markets, and customers. Custom scores can incorporate generic risk scores, traditional credit data, alternative credit data* (or expanded FCRA-regulated data), and a lender's proprietary data to increase their effectiveness. About 41 percent of consumer lending organizations use a model-first approach, and 55 percent use a score-first approach to credit decisioning.1 However, these aren't entirely exclusive groupings. For example, a credit score may be an input in a lender's credit risk model — almost every lender (99 percent) that uses credit risk models for decisioning also uses credit scores.2 Similarly, lenders that primarily rely on credit scores may also have business policies that affect their decisions. What are the current challenges? Risk departments and teams are facing several overarching challenges today: Staying flexible: Volatile market conditions and changing consumer preferences can lead to unexpected shifts in risk. Organizations need to actively monitor customer accounts and larger economic trends to understand when, if, and how they should adjust their risk policies. Digesting an overwhelming amount of data: More data can be beneficial, but only if it offers real insights and the organization has the resources to understand and use it efficiently. Artificial intelligence (AI) and machine learning (ML) are often important for turning raw data into actionable insights. Retaining IT talent: Many organizations are trying to figure out how to use vast amounts of data and AI/ML effectively. However, 82 percent of lenders have trouble hiring and retaining data scientists and analysts.3 Separating fraud and credit losses: Understanding a portfolio's credit losses can be important for improving credit risk models and performance. But some organizations struggle to properly distinguish between the two, particularly when synthetic identity fraud is involved. Best practices for credit risk management Leading financial institutions have moved on from legacy systems and outdated risk models or scores. And they're looking at the current challenges as an opportunity to pull away from the competition. Here's how they're doing it: Using additional data to gain a holistic picture: Lenders have an opportunity to access more data sources, including credit data from alternative financial services and consumer-permissioned data. When combined with traditional credit data, credit scores, and internal data, the outcome can be a more complete picture of a consumer's credit risk. Implementing AI/ML-driven models: Lenders can leverage AI/ML to analyze large amounts of data to improve organizational efficiency and credit risk assessments. 16 percent of consumer lending organizations expect to solely use ML algorithms for credit decisioning, while two-thirds expect to use both traditional and ML models going forward.4 Increasing model velocity: On average, it takes about 15 months to go from model development to deployment. But some organizations can do it in less than six.5 Increasing model velocity can help organizations quickly respond to changing consumer and economic conditions. Even if rapid model creation and deployment isn't an option, monitoring model health and recalibrating for drift is important. Nearly half (49 percent) of lenders check for model drift monthly or quarterly — one out of ten get automated alerts when their models start to drift.6 WATCH: Accelerating Model Velocity in Financial Institutions Improving automation and customer experience Lenders are using AI to automate their application, underwriting, and approval processes. Often, automation and ML-driven risk models go hand-in-hand. Lenders can use the models to measure the credit risk of consumers who don't qualify for traditional credit scores and automation to expedite the review process, leading to an improved customer experience. Learn more by exploring Experian's credit risk solutions. Learn more * When we refer to “Alternative Credit Data," this refers to the use of alternative data and its appropriate use in consumer credit lending decisions as regulated by the Fair Credit Reporting Act (FCRA). Hence, the term “Expanded FCRA Data" may also apply in this instance and both can be used interchangeably. 1-6. Experian (2023). Accelerating Model Velocity in Financial Institutions

With great risk comes great reward, as the saying goes. But when it comes to business, there's huge value in reducing and managing that risk as much as possible to maximize benefits — and profits. In today's high-tech strategic landscape, financial institutions and other organizations are increasingly using risk modeling to map out potential scenarios and gain a clearer understanding of where various paths may lead. But what are risk models really, and how can you ensure you're creating and using them correctly in a way that actually helps you optimize decision-making? Here, we explore the details. What is a risk model? A risk model is a representation of a particular situation that's created specifically for the purpose of assessing risk. That risk model is then used to evaluate the potential impacts of different decisions, paths and events. From assigning interest rates and amortization terms to deciding whether to begin operating in a new market, risk models are a safe way to analyze data, test assumptions and visualize potential scenarios. Risk models are particularly valuable in the credit industry. Credit risk models and credit risk analytics allow lenders to evaluate the pluses and minuses of lending to clients in specific ways. They are able to consider the larger economic environment, as well as relevant factors on a micro level. By integrating risk models into their decision-making process, lenders can refine credit offerings to fit the assessed risk of a particular situation. It goes like this: a team of risk management experts builds a model that brings together comprehensive datasets and risk modeling tools that incorporate mathematics, statistics and machine learning. This predictive modeling tool uses advanced algorithmic techniques to analyze data, identify patterns and make forecasts about future outcomes. Think of it as a crystal ball — but with science behind it. Your team can then use this risk model for a wide range of applications: refining marketing targets, reworking product offerings or reshaping business strategies. How can risk models be implemented? Risk models consolidate and utilize a wide variety of data sets, historical benchmarks and qualitative inputs to model risk and allow business leaders to test assumptions and visualize the potential results of various decisions and events. Implementing risk modeling means creating models of systems that allow you to adjust variables to imitate real-world situations and see what the results might be. A mortgage lender, for example, needs to be able to predict the effects of external and internal policies and decisions. By creating a risk model, they can test how scenarios such as falling interest rates, rising unemployment or a shift in loan acceptance rates might affect their business — and make moves to adjust their strategies accordingly. One aspect of risk modeling that can't be underestimated is the importance of good data, both quantitative and qualitative. Efforts to implement or expand risk modeling should begin with refining your data governance strategy. Maximizing the full potential of your data also requires integrating data quality solutions into your operations in order to ensure that the building blocks of your risk model are as accurate and thorough as possible. It's also important to ensure your organization has sufficient model risk governance in place. No model is perfect, and each comes with its own risks. But these risks can be mitigated with the right set of policies and procedures, some of which are part of regulatory compliance. With a comprehensive model risk management strategy, including processes like back testing, benchmarking, sensitivity analysis and stress testing, you can ensure your risk models are working for your organization — not opening you up to more risk. How can risk modeling be used in the credit industry? Risk modeling isn't just for making credit decisions. For instance, you might model the risk of opening or expanding operations in an underserved country or the costs and benefits of existing one that is underperforming. In information technology, a critical branch of virtually every modern organization, risk modeling helps security teams evaluate the risk of malicious attacks. Banking and financial services is one industry for which understanding and planning for risk is key — not only for business reasons but to align with relevant regulations. The mortgage lender mentioned above, for example, might use credit risk models to better predict risk, enhance the customer journey and ensure transparency and compliance. It's important to highlight that risk modeling is a guide, not a prophecy. Datasets can contain flaws or gaps, and human error can happen at any stage.. It's also possible to rely too heavily on historical information — and while they do say that history repeats itself, they don't mean it repeats itself exactly. That's especially true in the presence of novel challenges, like the rise of artificial intelligence. Making the best use of risk modeling tools involves not just optimizing software and data but using expert insight to interpret predictions and recommendations so that decision-making comes from a place of breadth and depth. Why are risk models important for banks and financial institutions? In the world of credit, optimizing risk assessment has clear ramifications when meeting overall business objectives. By using risk modeling to better understand your current and potential clients, you are positioned to offer the right credit products to the right audience and take action to mitigate risk. When it comes to portfolio risk management, having adequate risk models in place is paramount to meet targets. And not only does implementing quality portfolio risk analytics help maximize sales opportunities, but it can also help you identify risk proactively to avoid costly mistakes down the road. Risk mitigation tools are a key component of any risk modeling strategy and can help you maintain compliance, expose potential fraud, maximize the value of your portfolio and create a better overall customer experience. Advanced risk modeling techniques In the realm of risk modeling, the integration of advanced techniques like machine learning (ML) and artificial intelligence (AI) is revolutionizing how financial institutions assess and manage risk. These technologies enhance the predictive power of risk models by allowing for more complex data processing and pattern recognition than traditional statistical methods. Machine learning in risk modeling: ML algorithms can process vast amounts of unstructured data — such as market trends, consumer behavior and economic indicators — to identify patterns that may not be visible to human analysts. For instance, ML can be used to model credit risk by analyzing a borrower’s transaction history, social media activities and other digital footprints to predict their likelihood of default beyond traditional credit scoring methods. Artificial intelligence in decisioning: AI can automate the decisioning process in risk management by providing real-time predictions and risk assessments. AI systems can be trained to make decisions based on historical data and can adjust those decisions as they learn from new data. This capability is particularly useful in credit underwriting where AI algorithms can make rapid decisions based on market conditions. Financial institutions looking to leverage these advanced techniques must invest in robust data infrastructure, skilled personnel who can bridge the gap between data science and financial expertise, and continuous monitoring systems to ensure the models perform as expected while adhering to regulatory standards. Challenges in risk model validation Validating risk models is crucial for ensuring they function appropriately and comply with regulatory standards. Validation involves verifying both the theoretical foundations of a model and its practical implementation. Key challenges in model validation: Model complexity: As risk models become more complex, incorporating elements like ML and AI, they become harder to validate. Complex models can behave in unpredictable ways, making it difficult to understand why they are making certain decisions (the so-called "black box" issue). Data quality and availability: Effective validation requires high-quality, relevant data. Issues with data completeness, accuracy or relevance can lead to incorrect model validations. Regulatory compliance: With regulations continually evolving, keeping risk models compliant can be challenging. Different jurisdictions may have varying requirements, adding to the complexity of validation processes. Best practices: Regular reviews: Continuous monitoring and periodic reviews help ensure that models remain accurate over time and adapt to changing market conditions. Third-party audits: Independent reviews by external experts can provide an unbiased assessment of the risk model’s performance and compliance. These practices help institutions maintain the reliability and integrity of their risk models, ensuring that they continue to function as intended and comply with regulatory requirements. Read more: Blog post: What is model governance? How Experian can help Risk is inherent to business, and there's no avoiding it entirely. But integrating credit risk modeling into your operations can ensure stability and profitability in a rapidly evolving business landscape. Start with Experian's credit modeling services, which use expansive data, analytical expertise and the latest credit risk modeling methodologies to better predict risk and accelerate growth. Learn more *This article includes content created by an AI language model and is intended to provide general information.

Credit risk management best practices have been established and followed for years, but new technology and data sources offer lenders an opportunity to refine their credit risk management strategies.   What is credit risk management? Credit risk is the possibility that a borrower will not repay a debt as agreed. And credit risk management is the art and science of using risk mitigation tools to minimize losses while maximizing profits from lending activity.   Lenders can create credit underwriting criteria for each of their products and use risk-based pricing to alter the terms of a loan or line of credit based on the risk associated with the product and borrower. Credit portfolio management goes beyond originations and individual decisions to consider portfolios at large.   CASE STUDY: Atlas Credit worked with Experian to create a machine learning-powered model, optimize risk score cutoffs and automate their underwriting. The small-dollar lender nearly doubled its loan approval rates while reducing its losses by up to 20 percent. Why is credit risk management important? Continually managing credit risk matters because there's always a balancing act.   Tightening a credit box — using more restrictive underwriting criteria — might reduce credit losses. However, it can also decrease approval rates that would exclude borrowers who would have repaid as agreed. Expanding a credit box might increase approval rates but is only beneficial if the profit from good new loans exceeds credit losses.   Fraud is also on the rise and becoming more complex, making fraud management an important part of understanding risk. For instance, with synthetic identity fraud, fraudsters might “age an account" or make on-time payments before, “busting out” or maxing out a credit card and then abandoning the account.  If you look at payment activity alone, it might be hard to classify the loss as a fraud loss or credit loss.  Additionally, external economic forces and consumer behavior are constantly in flux. Financial institutions need effective consumer risk management and to adjust their strategies to limit losses. And they must dynamically adjust their underwriting criteria to account for these changes. You could be pushed off balance if you don't react in time. What does managing credit risk entail? Lenders have used the five C’s of credit to measure credit risk and make lending decisions for decades:  Character: The likelihood a borrower will repay the loan as agreed, often measured by analyzing their credit report and a credit risk score.   Capacity: The borrower's ability to pay, which lenders might measure by reviewing their outstanding debt, income, and debt-to-income ratio.   Capital: The borrower's commitment to the purchase, such as their down payment when buying a vehicle or home.   Collateral: The value of the collateral, such as a vehicle or home for an auto loan or mortgage.   Conditions: The external conditions that can impact a borrower's ability to afford payments, such as broader economic trends.  Credit risk management considers these within the context of a lender’s goals and its specific lending products. For example, capital and collateral aren't relevant for unsecured personal loans, which makes character and capacity the primary drivers of a decision.   Credit risk management best practices at origination Advances in analytics, computing power and real-time access to additional data sources are helping lenders better measure some of the C’s.   For example, credit risk scores can more precisely assess character for a lender's target market than generic risk scores. And open banking data allows lenders to more accurately understand a borrower's capacity by directly analyzing their cash flows.   With these advances in mind, leading lenders:  View underwriting as a dynamic process: Lenders have always had to respond to changing forces, and the pandemic highlighted the need to be nimble. Consider how you can use analytical insights to quickly adjust your strategies.   Test the latest credit risk modeling techniques: Artificial intelligence (AI) and machine learning (ML) techniques can improve credit risk model performance and drive automated credit risk decisioning. We've seen ML models consistently outperform traditional credit risk models by 10 to 15 percent.¹ Use multiple data sources: Alternative credit data* and consumer-permissioned data offer increased and real-time visibility into borrowers' creditworthiness. These additional data sources can also help fuel ML credit risk models.   Expand their lending universe: Alternative data can also help lenders more accurately assess the credit risk of the 49 million Americans who don't have a credit file or aren't scoreable by conventional models.² At the same time, they consciously remove biases from their decisions to increase financial inclusion.  READ: The Getting AI-driven decisioning right in financial services white paper explores trends, advantages, challenges and best practices for using AI in decisioning.   Experian helps lenders measure and manage credit risk Experian can trace its history of helping companies manage their credit risk back to 1803.³ Of course, a lot has changed since then, and today Experian is a leading provider of traditional credit data, alternative credit data and credit risk analytics.   For those who want to quickly benefit from the latest technological advancements, our Lift Premium™ credit risk model uses traditional and alternative data to score up to 96 percent of U.S. consumers — compared to the 81 percent that conventional models can score.4 Experian’s Ascend Platform and Ascend Intelligence Services™ can help lenders develop, deploy and monitor custom credit risk models to optimize their decisions.    With end-to-end platforms, our account and portfolio management services can help you limit risk, detect fraud, automate underwriting and identify opportunities to grow your business.   Learn more about Experian's approach to credit risk management ¹Experian (2020). Machine Learning Decisions in Milliseconds ²Oliver Wyman (2022). Financial Inclusion and Access to Credit ³Experian (2013). A Brief History of Experian 4Experian (2023). Lift Premium™ and Lift Plus™ *When we refer to “Alternative Credit Data," this refers to the use of alternative data and its appropriate use in consumer credit lending decisions, as regulated by the Fair Credit Reporting Act. Hence, the term “Expanded FCRA Data" may also apply and can be used interchangeably.

The science of turning historical data into actionable insights is far from magic. And while organizations have successfully used predictive analytics for years, we're in the midst of a transformation. New tools, vast amounts of data, enhanced computing power and decreasing implementation costs are making predictive analytics increasingly accessible. And business leaders from varying industries and functions can now use the outcomes to make strategic decisions and manage risk. What is predictive analytics? Predictive analytics is a type of data analytics that uses statistical modeling and machine learning techniques to make predictions based on historical data. Organizations can use predictive analytics to predict risks, needs and outcomes. You might use predictive analytics to make an immediate decision. For example, whether or not to approve a new credit application based on a credit score — the output from a predictive credit risk model. But organizations can also use predictive analytics to make long-term decisions, such as how much inventory to order or staff to hire based on expected demand. How can predictive business analytics help a business succeed? Businesses can use predictive analytics in different parts of their organizations to answer common and critical questions. These include forecasting market trends, inventory and staffing needs, sales and risk. With a wide range of potential applications, it’s no surprise that organizations across industries and functions are using predictive analytics to inform their decisions. Here are a few examples of how predictive analytics can be helpful: Financial services: Financial institutions can use predictive analytics to assess credit risk, detect fraudulent applicants or transactions, cross-sell customers and limit losses during recovery. Healthcare: Using data from health records and medical devices, predictive models can predict patient outcomes or identify patients who need critical care. Manufacturing: An organization can use models to predict when machines need to be turned off or repaired to improve their longevity and avoid accidents. Retail: Brick-and-mortar retailers might use predictive analytics when deciding where to expand, what to cross-sell loyalty program members and how to improve pricing. Hospitality: A large hospitality group might predict future reservations to help determine how much staff they need to hire or schedule. Advanced techniques in predictive modeling for financial services Emerging technologies, particularly AI and machine learning (ML), are revolutionizing predictive modeling in the financial sector by providing more accurate, faster and more nuanced insights. Taking a closer look at financial services, consider how an organization might use predictive credit analytics and credit risk scores across the customer lifecycle. Marketing: Segment consumers to run targeted marketing campaigns and send prescreened credit offers to the people who are most likely to respond. AI models can analyze customer data to offer personalized offers and product recommendations. Underwriting: AI technologies enable real-time data analysis, which is critical for underwriting. The outputs from credit risk models can help you to quickly approve, deny or send applications for manual review. Explainable machine learning models may be able to expand automation and outperform predictive models built with older techniques by 10 to 15 percent.1 Fraud detection models can also raise red flags based on suspicious information or behaviors. Account management: Manage portfolios and improve customer retention, experience and lifetime value. The outputs can help you determine when you should adjust credit lines and interest rates or extend offers to existing customers. AI can automate complex decision-making processes by learning from historical data, reducing the need for human intervention and minimizing human error. Collections: Optimize and automate collections based on models' predictions about consumers' propensity to pay and expected recovery amounts. ML models, which are capable of processing vast amounts of unstructured data, can uncover complex patterns that traditional models might miss. Although some businesses can use unsupervised or “black box" models, regulations may limit how financial institutions can use predictive analytics to make lending decisions. Fortunately, there are ways to use advanced analytics, including AI and ML, to improve performance with fully compliant and explainable credit risk models and scores. WHITE PAPER: Getting AI-driven decisioning right in financial services Developing predictive analytics models Going from historical data to actionable analytics insights can be a long journey. And if you're making major decisions based on a model's predictions, you need to be confident that there aren’t any missteps along the way. Internal and external data scientists can oversee the process of developing, testing and implementing predictive analytics models: Define your goal: Determine the predictions you want to make or problems you want to solve given the constraints you must act within. Collect data: Identify internal and external data sources that house information that could be potentially relevant to your goal. Prepare the data: Clean the data to prepare it for analysis by removing errors or outliers and determining if more data will be helpful. Develop and validate models: Create predictive models based on your data, desired outcomes and regulatory requirements. Deciding which tools and techniques to use during model development is part of the art that goes into the science of predictive analytics. You can then validate models to confirm that they accurately predict outcomes. Deploy the models: Once a model is validated, deploy it into a live environment to start making predictions. Depending on your IT environment, business leaders may be able to easily access the outputs using a dashboard, app or website. Monitor results: Test and monitor the model to ensure it's continually meeting performance expectations. You may need to regularly retrain or redevelop models using training data that better reflects current conditions. Depending on your goals and resources, you may want to start with off-the-shelf predictive models that can offer immediate insights. But if your resources and experience allow, custom models may offer more insights. CASE STUDY: Experian worked with one of the largest retail credit card issuers to develop a custom acquisition model. The client's goal was to quickly replace their outdated custom model while complying with their model governance requirements. By using proprietary attribute sets and a patented advanced model development process, Experian built a model that offered 10 percent performance improvements across segments. Predictive modeling techniques Data scientists can use different modeling techniques when building predictive models, including: Regression analysis: A traditional approach that identifies the most important relationships between two or more variables. Decision trees: Tree-like diagrams  show potential choices and their outcomes. Gradient-boosted trees: Builds on the output from individual decision trees to train more predictive trees by identifying and correcting errors. Random forest: Uses multiple decision trees that are built in parallel on slightly different subsets of the training data. Each tree will give an output, and the forest can analyze all of these outputs to determine the most likely result. Neural networks: Designed to mimic how the brain works to find underlying relationships between data points through repeated tests and pattern recognition. Support vector machines: A type of machine learning algorithm that can classify data into different groups and make predictions based on shared characteristics. Experienced data scientists may know which techniques will work well for specific business needs. However, developing and comparing several models using different techniques can help determine the best fit. Implementation challenges and solutions in predictive analytics Integrating predictive analytics into existing systems presents several challenges that range from technical hurdles to external scrutiny. Here are some common obstacles and practical solutions: Data integration and quality: Existing systems often comprise disparate data sources, including legacy systems that do not easily interact. Extracting high-quality data from these varied sources is a challenge due to inconsistent data formats and quality. Implementing robust data management practices, such as data warehousing and data governance frameworks, ensure data quality and consistency. The use  of APIs can facilitate seamless data integration. Scalability: Predictive business analytics models that perform well in a controlled test environment may not scale effectively across the entire organization. They can suffer from performance issues when deployed on a larger scale due to increased data volumes and transaction rates. Invest in scalable infrastructure, such as cloud-based platforms that can dynamically adjust resources based on demand. Regulatory compliance: Financial institutions are heavily regulated, and any analytics tool must comply with existing laws — such as the Fair Credit Reporting Act in the U.S. — which govern data privacy and model transparency. Including explainable AI capabilities helps to ensure transparency and compliance in your predictive models. Compliance protocols should be regularly reviewed to align with both internal audits and external regulations. Expertise: Predictive analytics requires specialized knowledge in data science, machine learning and analytics. Develop in-house expertise through training and development programs or consider partnerships with analytics firms to bridge the gap. By addressing these challenges with thoughtful strategies, organizations can effectively integrate predictive analytics into their systems to enhance decision-making and gain a competitive advantage. From prediction to prescription While prediction analytics focuses on predicting what may happen, prescription analytics focuses on what you should do next. When combined, you can use the results to optimize decisions throughout your organization. But it all starts with good data and prediction models. Learn more about Experian's predictive modeling solutions. 1Experian (2020). Machine Learning Decisions in Milliseconds *This article includes content created by an AI language model and is intended to provide general information.

Machine learning (ML) is a powerful tool that can consume vast amounts of data to uncover patterns, learn from past behaviors, and predict future outcomes. By leveraging ML-powered credit risk models, lenders can better determine the likelihood that a consumer will default on a loan or credit obligation, allowing them to score applicants more accurately. When applied to credit decisioning, lenders can achieve a 25 percent reduction in exposure to risky customers and a 35 percent decrease in non-performing loans.1 While ML-driven models enable lenders to target the right audience and control credit losses, many organizations face challenges in developing and deploying these models. Some still rely on traditional lending models with limitations preventing them from making fast and accurate decisions, including slow reaction times, fewer data sources, and less predictive performance. With a trusted and experienced partner, financial institutions can create and deploy highly predictive ML models that optimize their credit decisioning. Case study: Increase customer acquisition with improved predictive performance Looking to meet growth goals without increasing risk, a consumer goods retailer sought out a modern and flexible solution that could help expand its finance product options. This meant replacing existing ML models with a custom model that offers greater transparency and predictive power. The retailer partnered with Experian to develop a transparent and explainable ML model. Based on the model’s improved predictive performance, transparency, and ability to derive adverse action reasons for declines, the retailer increased sales and application approval rates while reducing credit risk. Read the case study Learn about our custom modeling capabilities 1 Experian (2020). The Art of Decisioning in Uncertain Times

Credit reports and conventional credit scores give lenders a strong starting point for evaluating applicants and managing risk. But today's competitive environment often requires deeper insights, such as credit attributes. Experian develops industry-leading credit attributes and models using traditional methods, as well as the latest techniques in machine learning, advanced analytics and alternative credit data — or expanded Fair Credit Reporting Act (FCRA)-regulated data)1 to unlock valuable consumer spending and payment information so businesses can drive better outcomes, optimize risk management and better serve consumers READ MORE: Using Alternative Credit Data for Credit Underwriting Turning credit data into digestible credit attributes Lenders rely on credit attributes — specific characteristics or variables based on the underlying data — to better understand the potentially overwhelming flow of data from traditional and non-traditional sources. However, choosing, testing, monitoring, maintaining and updating attributes can be a time- and resource-intensive process. Experian has over 45 years of experience with data analytics, modeling and helping clients develop and manage credit attributes and risk management. Currently, we offer over 4,500 attributes to lenders, including core attributes and subsets for specific industries. These are continually monitored, and new attributes are released based on consumer trends and regulatory requirements. Lenders can use these credit attributes to develop precise and explainable scoring models and strategies. As a result, they can more consistently identify qualified prospects that might otherwise be missed, set initial limits, manage credit lines, improve loyalty by applying appropriate treatments and limit credit losses. Using expanded credit data effectively Leveraging credit attributes is critical for portfolio growth, and businesses can use their expanding access to credit data and insights to improve their credit decisioning. A few examples: Spot trends in consumer behavior: Going beyond a snapshot of a credit report, Trended 3DTM attributes reveal and make it easier to understand customers' behavioral patterns. Use these insights to determine when a customer will likely revolve, transact, transfer a balance or fall into distress. Dig deeper into credit data: Making sense of vast amounts of credit report data can be difficult, but Premier AttributesSM  aggregates and summarizes findings. Lenders use the 2,100-plus attributes to segment populations and define policy rules. From prospecting to collections, businesses can save time and make more informed decisions across the customer lifecycle. Get a clear and complete picture: Businesses may be able to more accurately assess and approve applicants, simply by incorporating attributes overlooked by traditional credit bureau reports into their decisioning process. Clear View AttributesTM uses data from the largest alternative financial services specialty bureau, Clarity Services, to show how customers have used non-traditional lenders, including auto title lenders, rent-to-own and small-dollar credit lenders. The additional credit attributes and analysis help lenders make more strategic approval and credit limit decisions, leading to increased customer loyalty, reduced risk and business growth. Additionally, many organizations find that using credit attributes and customized strategies can be important for measuring and reaching financial inclusion goals. Many consumers have a thin credit file (fewer than five credit accounts), don’t have a credit file or don’t have information for conventional scoring models to score them. Expanded credit data and attributes can help lenders accurately evaluate many of these consumers and remove barriers that keep them from accessing mainstream financial services. There's no time to wait Businesses can expand their customer base while reducing risk by looking beyond traditional credit bureau data and scores. Download our latest e-book on credit attributes to learn more about what Experian offers and how we can help you stay ahead of the competition.  Download e-book  Learn more 1When we refer to “Alternative Credit Data," this refers to the use of alternative data and its appropriate use in consumer credit lending decisions, as regulated by the Fair Credit Reporting Act. Hence, the term “Expanded FCRA Data" may also apply in this instance and both can be used interchangeably.

Many financial institutions have made inclusion a strategic priority to expand their reach and help more U.S. consumers access affordable financial services. To drive deeper understanding, Experian commissioned Forrester to do new research to identify key focal points for firms and how they are moving the needle. The study found that more than two-thirds of institutions had a strategy created and implemented while one-quarter reported they are already up and running with their inclusion plans.1 Tapping into the underserved The research examines the importance of engaging new audiences such as those that are new to credit, lower-income, thin file, unbanked and underbanked as well as small businesses. To tap into these areas, the study outlines the need to develop new products and services, adopt willingness to change policies and processes, and use more data to drive better decisions and reach.2 Expanded data for improved risk decisioning The research underlines the use of alternative data and emerging technologies to expand reach to new audiences and assist many who have been underserved. In fact, sixty-two percent of financial institutions surveyed reported they currently use or are planning to use expanded data to improve risk profiling and credit decisions, with focus on: Banking data Cash flow data Employment verification data Asset, investments, and wealth management data Alternative financial services data Telcom and utility data3 Join us to learn more at our free webinar “Reaching New Heights Together with Financial Inclusion” where detailed research and related tools will be shared featuring Forrester’s principal analyst on Tuesday, May 24 from 10 – 11 a.m. PT. Register here for more information. Find more financial inclusion resources at www.experian.com/inclusionforward. Register for webinar Visit us 1 Based on Forrester research 2 Ibid. 3 Ibid.

It is no news that businesses are increasing their focus on advanced analytics and models. Whether looking to increase resources or focus on artificial intelligence (AI) and machine learning (ML), growth is the name of the game. But how do you maximize impact while minimizing risk? And how can you secure expertise and ROI when budgets are strapped?  Does your organization have the knowledge and talent in-house to remain competitive? No matter where you are on the analytics maturity curve, (outlined in detail below), your organization can benefit from making sure your machine learning models solution consists of: Regulatory documentation: Documentation for model and strategy governance is critical, especially as there is more conversation surrounding fair lending and how it relates to machine learning models. How does your organization ensure your models are explainable, well documented and making fair decisions? These are all questions you must be asking of your partners and solutions. Integrated services: For some service providers, “integrated,” is merely a marketing ploy, but it is essential that your solution truly integrates attributes, scores, models and decisions into one another. Not only does this serve as a “checks and balances” system of sorts, but it also is a primary driver for the speed of decisioning, which is crucial in today’s digital-first world. Deep expertise: Models are a major component for your decisioning, but ensuring those models are built and backed by experts is the one-two punch your strategies depend on. Make sure your services are managed by data scientists with extensive experience to take the best approach to solving your business problems. Usability: Does your solution close the loop? To future proof your processes, your solution must analyze the performance of attributes, scores and strategies. On top of that, your solution should make sure the items being built are useable and can be modified when needed. A one-and-done model does not suit the unique needs of your organization, so ensure your solution provides actionable analysis for continual refinement. Does your machine learning model solution check these boxes? Do you want to transform your existing system into a state-of-the-art AI platform? Learn more about how you can take your business challenges head-on by rapidly developing, deploying and monitoring sophisticated models and strategies to more accurately predict risk and achieve better outcomes. Learn more Access infographic   More information: What’s the analytics maturity curve? “Analytics” is the discovery, interpretation and communication of meaningful patterns in data; the connective tissue between data and effective decision-making within an organization. You can be along this journey for different decision points you’re making or product types, said Mark Soffietti, Director of Analytics Consulting at Experian, at our recent AI-driven analytics and strategy optimization webinar. Where you are on this curve often depends on your organization’s use of generic versus custom scores, the systems currently engaged to make those decisions and the sophistication of an organization’s models and/or strategies. Here’s a breakdown of each of the four stages: Descriptive Analytics – Descriptive analytics is the first step of the analytics maturity curve. These analytics answer the question “What is happening?” and typically revolve around some form of reporting. An example would be the information that your organization received 100 applications. Diagnostic Analytics – These analytics move from what happened to, “Why did it happen?” By digging into the 100 applications received, diagnostic analytics answer questions like “Who were we targeting?” and “How did those people come into our online portal/branch?” This information helps organizations be more strategic in their practices. Predictive Analytics – Models come into play at this stage as organizations try to predict what will happen. Based on the data set and an understanding of what the organization is doing, effort is put towards automating information to better solve business problems. Prescriptive Analytics – Optimization is key for prescriptive analytics. At this point in the maturity curve, there are multiple models and/or information that may be competing against one another. Prescriptive analytics will attempt to prescribe what an organization is doing and how it can drive more desired behaviors. For more information and to get personalized recommendations throughout your analytics journey, visit our website.

Credit cards are the most widely available credit products offered to millions of consumers today. For many consumers, owning a credit card is a relatively simple step toward establishing credit history and obtaining access to other lending products later in life. For credit unions, offering a credit card to members expands and enriches the credit relationship. In today’s environment, some credit unions don’t view credit cards as an integral part of their member service. I propose that the benefits of credit cards in a credit union portfolio are impactful, meaningful and fully align to member outreach and community service. A high-level review of risk-adjusted yields across three of the most common retail products offered by credit unions show that credit cards can be very profitable. The average APR of credit cards as of Q3 2020 is just slightly below personal loans. While charge-offs as a percentage of balances are more than double of personal loans, the estimated risk-adjusted yield is still elevated and is 1.8 times higher than auto loan and leases. See Table 1. Table 1. Estimated average risk-adjusted yield for auto loan and lease, personal loan, and credit card for credit unions Auto loan and lease Personal loan Credit card Average APR 5.21% 12.05% 11.26% Charge-offs as % of balances (annualized) 0.28% 0.89% 1.98% Risk-adjusted yield 4.93% 11.16% 9.28% Notes: Average APR of auto loans and leases, personal loans, and charge-off information as of Q3 2020 was extracted from Experian-Oliver Wyman IntelliViewSM Market Intelligence Reports. IntelliView Market Intelligence Reports, Dec. 22, 2020, experian.com/decision-analytics/market-intelligence/intelliview. Average APR of credit card as of Q3 2020 was extracted from National Credit Union Administration website. Credit Union and Bank Rates 2020 Q3, Dec. 22, 2020, https://www.ncua.gov/analysis/cuso-economic-data/credit-union-bank-rates/credit-union-and-bank-rates-2020-q3. Estimated risk-adjusted yield is calculated as the difference between average APR and charge-offs. A profitable retail product allows a credit union to share those profits back with members consistent with its mission of promoting and supporting the financial health and well-being of its members. Credit cards provide diversification of income streams. Income diversification provides a level of stability across cyclical economic conditions when some types of credit exposures may perform poorly, while others may be more stable. When combined with sound and effective risk governance, credit diversification allows lenders to mitigate levels of concentration risks in their aggregate portfolio. Offering credit cards to members is one avenue to grow loan volume and achieve scale that’s sufficiently manageable for credit unions. Scale is particularly important today as it’s needed to fund technology investments. The pandemic accelerated the massive movement toward digital engagement, and scale makes technology investments more cost-effective.  When lenders become more productive and efficient, they further lower the cost of credit products to members. (Stovall, Nathan. Dec. 14, 2020. Desire to compete with megabanks driving more U.S. regional bank M&A — KBW CE blog. https://platform.mi.spglobal.com/web/client?auth=inherit#news/.) The barriers to offering credit cards have moderately declined. Technology partners, payment processors and specialized industry companies are available in the marketplace. The biggest challenge for credit unions and lenders is credit risk management. To be profitable and to stay relevant, credit cards require a relatively sophisticated risk management framework of underwriting criteria, pricing, credit line management, operations and marketing. Industry and specialized support for launching and managing credit cards is widely available and accessible. Analytics play an essential role in managing credit cards. With an average active life of approximately five years, credit card portfolios need regular and periodic performance reviews to manage inherent risk and to identify opportunities for growth and profitability. Account management for credit cards is equally as important as underwriting. Credit line management, authorization, activation and retention have significant impact to the performance of existing accounts. Continuous engagement with members is critical and has taken on a new meaning lately. Credit cards provide an opportunity to engage members, to grow lending relationships and to support financial well-being. Marketing and meaningful card offers drive card usage and relevance. They’re critical components in customer communication and service. The benefits of credit cards contribute positively to a credit union portfolio. With sound and effective risk management practices, credit cards are profitable, help diversify income streams, grow loan volume and support member credit needs.

Intuitively we all know that people with higher credit risk scores tend to get more favorable loan terms. Since a higher credit risk score corresponds to lower chance of delinquency, a lender can grant: a higher credit line, a more favorable APR or a mix of those and other loan terms. Some people might wonder if there is a way to quantify the relationship between a credit risk score and the loan terms in a more mathematically rigorous way. For example, what is an appropriate credit limit for a given score band? Early in my career I worked a lot with mathematical optimization. This optimization used a software product called Marketswitch (later purchased by Experian). One caveat of optimization is in order to choose an optimal decision you must first simulate all possible decisions. Basically, one decision cannot be deemed better than another if the consequences of those decisions are unknown. So how does this relate to credit risk scores? Credit scores are designed to give lenders an overall view of a borrower’s credit worthiness. For example, a generic risk score might be calibrated to perform across: personal loans, credit cards, auto loans, real estate, etc. Per lending category, the developer of the credit risk score will provide an “odds chart;” that is, how many good outcomes can you expect per bad outcome. Here is an odds chart for VantageScore® 3 (overall - demi-decile). Score Range How Many Goods for 1 Bad 823-850 932.3 815-823 609.0 808-815 487.6 799-808 386.1 789-799 272.5 777-789 228.1 763-777 156.1 750-763 115.6 737-750 85.5 723-737 60.3 709-723 45.1 693-709 33.0 678-693 24.3 662-678 18.3 648-662 14.1 631-648 10.8 608-631 7.9 581-608 5.5 542-581 3.5 300-542 1.5 Per the above chart, there will be 932.3 good accounts for every one “bad” (delinquent) account in the score range of 823-850. Now, it’s a simple calculation to turn that into a bad rate (i.e. what percentage of accounts in this band will go bad). So, if there are 932.3 good accounts for every one bad account, we have (1 expected bad)/(1 expected bad + 932.3 expected good accounts) = 1/(1+932.3) = 0.1071%. So, in the credit risk band of 823-850 an account has a 0.1071% chance of going bad. It’s very simple to apply the same formula to the other risk bands as seen in the table below. Score Range How Many Goods for 1 Bad Bad Rate 823-850 932.3 0.1071% 815-823 609.0 0.1639% 808-815 487.6 0.2047% 799-808 386.1 0.2583% 789-799 272.5 0.3656% 777-789 228.1 0.4365% 763-777 156.1 0.6365% 750-763 115.6 0.8576% 737-750 85.5 1.1561% 723-737 60.3 1.6313% 709-723 45.1 2.1692% 693-709 33.0 2.9412% 678-693 24.3 3.9526% 662-678 18.3 5.1813% 648-662 14.1 6.6225% 631-648 10.8 8.4746% 608-631 7.9 11.2360% 581-608 5.5 15.3846% 542-581 3.5 22.2222% 300-542 1.5 40.0000%   Now that we have a bad percentage per risk score band, we can define dollars at risk per risk score band as: bad rate * loan amount = dollars at risk. For example, if the loan amount in the 823-850 band is set as $10,000 you would have 0.1071% * $10,000 = $10.71 at risk from a probability standpoint. So, to have constant dollars at risk, set credit limits per band so that in all cases there is $10.71 at risk per band as indicated below. Score Range How Many Goods for 1 Bad Bad Rate Loan Amount $ at Risk 823-850 932.3 0.1071%  $   10,000.00  $   10.71 815-823 609.0 0.1639%  $     6,535.95  $   10.71 808-815 487.6 0.2047%  $     5,235.19  $   10.71 799-808 386.1 0.2583%  $     4,147.65  $   10.71 789-799 272.5 0.3656%  $     2,930.46  $   10.71 777-789 228.1 0.4365%  $     2,454.73  $   10.71 763-777 156.1 0.6365%  $     1,683.27  $   10.71 750-763 115.6 0.8576%  $     1,249.33  $   10.71 737-750 85.5 1.1561%  $        926.82  $   10.71 723-737 60.3 1.6313%  $        656.81  $   10.71 709-723 45.1 2.1692%  $        493.95  $   10.71 693-709 33.0 2.9412%  $        364.30  $   10.71 678-693 24.3 3.9526%  $        271.08  $   10.71 662-678 18.3 5.1813%  $        206.79  $   10.71 648-662 14.1 6.6225%  $        161.79  $   10.71 631-648 10.8 8.4746%  $        126.43  $   10.71 608-631 7.9 11.2360%  $          95.36  $   10.71 581-608 5.5 15.3846%  $          69.65  $   10.71 542-581 3.5 22.2222%  $          48.22  $   10.71 300-542 1.5 40.0000%  $          26.79  $   10.71   In this manner, the output is now set credit limits per band so that we have achieved constant dollars at risk across bands. Now in practice it’s unlikely that a lender will grant $1,683.27 for the 763 to 777 credit score band but this exercise illustrates how the numbers are generated. More likely, a lender will use steps of $100 or something similar to make the credit limits seem more logical to borrowers. What I like about this constant dollars at risk approach is that we aren’t really favoring any particular credit score band. Credit limits are simply set in a manner that sets dollars at risk consistently across bands. One final thought on this: Actual observations of delinquencies (not just predicted by the scores odds table) could be gathered and used to generate a new odds tables per score band. From there, the new delinquency rate could be generated based on actuals. Though, if this is done, the duration of the sample must be long enough and comprehensive enough to include both good and bad observations so that the delinquency calculation is robust as small changes in observations can affect the final results. Since the real world does not always meet our expectations, it might also be necessary to “smooth” the odds-chart so that its looks appropriate.

Today, Experian and Oliver Wyman launched the Ascend Portfolio Loss ForecasterTM, a solution built to help lenders make better decisions – during COVID-19 and beyond – with customized forecasts and macroeconomic data. Phrases like “the new normal,” “unprecedented times,” and “extreme economic volatility” have flooded not only media for the last few months, but also financial institutions’ strategic discussions regarding plans to move forward. What has largely been crisis response is quickly shifting to an urgent need to answer the many questions around “Will we survive this crisis?,” let alone “What’s next?” And arguably, we’ve entered a new era of loss forecasting. After the longest period of economic growth in post-war U.S. history, previously built models are not sufficient for the unprecedented and sudden changes in economic conditions due to COVID-19. Lenders need instant insights to assess impact and losses to their portfolios. The Ascend Portfolio Loss Forecaster combines advanced modeling from Oliver Wyman,  pandemic-specific insights and macroeconomic scenarios from Oxford Economics, and Experian’s quality data to analyze and produce accurate loan loss forecasts. Additionally, all of the data, including the forecasts and models, are regularly updated as macroeconomic conditions change. “Experian’s agility and innovative technologies allow us to help lenders make informed decisions in real time to mitigate future risk,” said Greg Wright, chief product officer of Experian’s Consumer Information Services, in a recent press release. “We’re proud to work with our partners, Oxford Economics and Oliver Wyman, to bring lenders a product powered by machine learning, comprehensive data and macroeconomic forecast scenarios.” Built using advanced modeling and expert scenarios, the web-based application maximizes the more than 15 years of Experian’s loan-level data, including VantageScore® credit score, bankruptcy scores and customer-level attributes.  Financial institutions can gauge loan portfolio performance under various scenarios. “It is important that the banks take into account the evolving credit behaviors due to the COVID-19 pandemic, in addition to the robust modeling technique for their loss forecasting and strategic decisioning,” said Anshul Verma, senior director of products at Oliver Wyman, also in the release. “With the Ascend Portfolio Loss Forecaster, lenders get robust models that work in the current conditions and take into account evolving consumer behaviors,” Verma said. To watch Experian’s webinar on portfolio loss forecasting, please click here and to learn more about the Ascend Portfolio Loss Forecaster, click the button below. Learn More

While an overdue economic downturn has been long discussed, arguably no one could have foreseen the economic disruption from COVID-19 to the extent that’s been witnessed thus far. But now that we’re here, is there a line of sight to financial institutions’ next move? With the current situation marked by a history-making rise in unemployment, massive amounts of uncertainty within the market as well as for consumers and small businesses and consumer spending changes, loss forecasting is more important now than ever before. After the longest period of economic growth in history, financial institutions are caught off guard. While large banks are more prepared as they have stress testing capabilities in place and are estimating the potential large impact on their loss allowances, the since-delayed CECL requirements emphasized forecasting for the masses, and yet many are still under-equipped. Loss forecasting has evolved from a need for a small few to now a necessary strategy for all. While some financial institutions will look to loss forecasting to potentially reduce the severity of impact for the path ahead during these times (or even how they might come out stronger than their competition), for many, loss forecasting is the key to survival. Bare necessities. Understanding the possible outcomes of the pandemic’s impact is necessary to make critical business decisions. Lenders are likely receiving numerous questions about their portfolios and possible outcomes. These questions include, but are not limited to: What could the range of outcomes to my portfolio based on expert forecasts of macroeconomic conditions? How will I make lending decisions in the short term? Do my models need to change? How bad could charge offs be for my portfolio? If I have reduced marketing and application flows, at what point do I need to begin opening new accounts or consider portfolio acquisitions? How can lenders get answers? Loss forecasting. As Mohammed Chaudhri, Experian Chief Economist, said, “Loss forecasting is more pivotal than ever…existing models are not going to be up to the task of accurately predicting losses.” Whatever questions you’re receiving, you need certain necessary pieces of information to navigate this new era of loss forecasting. Those pieces are frequently updated client and industry data; ongoing access to expert macroeconomic forecasts; and sophisticated and evolved forecasting models. Client and Industry Data Loan-level data, bankruptcy scores and customer-level attributes are key insights to fueling loss forecasting models. By combining several data sets and scores (and a comprehensive history of both) your organization can see greater benefits. Macroeconomic Forecasts As has been mentioned numerous times, the economic impact resulting from COVID-19 is not at all like the Great Recession. As such, leveraging macroeconomic forecasts, and specifically COVID-19 forecasts, is critical to analyzing the potential impacts to your organization. Sophisticated Models Whether building models on your own or leveraging an expert, the key ingredients include the innerworkings of the model, leveraging historical data and making sure that both the models and the data are updated regularly to ensure you have the most accurate, thorough forecasts available. Also, leveraging machine learning tools is imperative for model specification and evaluation. Fortunately, while model building and loss forecasting used to be synonymous with countless resources and dollar signs, innovation and digital transformation have made these strategies within reach for financial institutions of all sizes. Incorporating the right data (and ensuring that data is regularly updated), with the right tools and macroeconomic scenarios (including COVID-19, upside, baseline, adverse and severely adverse scenarios) enables you to get a line of sight into the actions you need to take now. Empowered with insights to compare and benchmark results, discover the cause of changes in results, explore result scenarios in advance, and access recommended optimizations, loss forecasting enables you to focus on the critical decisions your business depends on. Experian helps you with loss forecasting for now and the future. For more information, including an on-demand webinar Experian presented with Oliver Wyman as well as the opportunity to engage Experian experts into your loss forecasting strategy, please click the button below. Learn More

This is the third in a series of blog posts highlighting optimization, artificial intelligence, predictive analytics, and decisioning for lending operations in times of extreme uncertainty. The first post dealt with optimization under uncertainty and the second with predicting consumer payment behavior. In this post I will discuss how well credit scores will work for consumer lenders during and after the COVID-19 crisis and offer some recommendations for what lenders can be doing to measure and manage that model risk in a time like this. Perhaps no analytics innovation has created opportunity for more individuals than the credit score has. The first commercially available credit score was developed by MDS (now part of Experian) in 1987. Soon afterwards FICO® popularized the use of scores that evaluate the risk that a consumer would default on a loan. Prior to that, lending decisions were made by loan officers largely on the basis on their personal familiarity with credit applicants. Using data and analytics to assess risk not only created economic opportunity for millions of borrowers, but it also greatly improved the financial soundness of lending institutions worldwide. Predictive models such as credit scores have become the most critical tools for consumer lending businesses. They determine, among other things, who gets a loan and at what price and how an account such as a credit line is managed through its life cycle. Predictive models are in many cases critical for calculating loan and loss reserves, for stress testing, and for complying with accounting standards. Nearly all lenders rely on generic scores such as the FICO® score and VantageScore® credit score. Most larger companies also have a portfolio of custom scorecards that better predict particular aspects of payment behavior for the customers of interest. So how well are these scorecards likely to perform during and after the current pandemic? The models need to predict consumer credit risk even as: Nearly all consumers change their behaviors in response to the health crisis, Millions of people—in America and internationally—find their income suddenly reduced, and Consumers receive large numbers of accommodations from creditors, who have in turn temporarily changed some of their credit reporting practices in response to guidelines in the federal CARES Act. In an earlier post, I pointed out that there is good reason to believe that credit scores will tend to continue to rank order consumers from most likely to least likely to repay their debts even as we move from the longest economic expansion in history to a period of unforeseen and unexpected challenges. But the interpretation of the score (for example, the log odds or the bad rate) may need to be adjusted. Furthermore, that assumes that the model was working well on a lender’s population before this crisis started. If it has been a long time since a scorecard was validated, that assumption needs to be questioned. Because experts are considering several different scenarios regarding both the immediate and long-term economic impacts of COVID-19, it’s important to have a plan for ongoing monitoring as long as necessary. Some lenders have strong Model Risk Management (MRM) teams complying with requirements from the Federal Reserve, Federal Deposit Insurance Corporation (FDIC), the Office of the Comptroller of the Currency (OCC). Those resources are now stretched thin. Other institutions, with fewer resources for MRM, are now discovering gaps in their model inventories as they implement operational changes. In either case, now’s the time to reassess how well scorecards are working. Good model validation practices are especially critical now if lenders are to continue to make the sound data-driven decisions that promote fairness for consumers and financial soundness for the institution. If you’re a credit risk manager responsible for the generic or custom models driving your lending, servicing, or capital allocation policies, there are several things you can do--starting now--to be sure that your organization can continue to make fair and sound lending decisions throughout this volatile period: Assess your model inventory. Do you have good documentation showing when each of the models in your organization was built? When was it last validated? Assign a level of criticality to each model in use. Starting with your most critical models, perform a baseline validation to determine how the model was performing prior to the global health crisis. It may be prudent to conduct not only your routine validation (verifying that the model was continuing to perform at the beginning of the period) but also a baseline validation with a shortened performance window (such as 6-12 months). That baseline validation will be useful if the downturn becomes a protracted one—in which case your scorecard models should be validated more frequently than usual. A shorter outcome window will allow a timelier assessment of the relationship between the score and the bad rate—which will help you update your lending and servicing policies to prevent losses. Determine if any of your scorecards had deteriorated even before the global pandemic. Consider recalibrating or rebuilding those scorecards. (Use metrics such as the Population Stability Index, the K-S statistic and the Gini Coefficient to help with that decision.) Many lenders chose not to prioritize rebuilding their behavioral scorecards for account management or collections during the longest period of economic growth in memory. Those models may soon be among the most critical models in your organization as you work to maintain the trust of your accountholders while also maintaining your institution’s financial soundness. Once the CARES accommodation period has expired, it will be important to revalidate your models more frequently than in the past—for as long as it takes until consumer behavior normalizes and the economy finds its footing. When you find it appropriate to rebuild a scorecard model, consider whether now is the time to implement ethical and explainable AI. Some of our clients are finding that Machine Learned models are more predictive than traditional scorecards. Early Experian research using data from the last recession indicates this will continue to be true for the foreseeable future. Furthermore, Experian has invested in Research and Development to help these clients deliver FCRA-compliant Adverse Action reasons to their consumers and to make the models explainable and transparent for model risk governance and compliance purposes. The sudden economic volatility that has resulted from this global health crisis has been a shock to all organizations. It is important for lenders to take the pulse of their predictive models now and throughout the downturn. They are especially critical tools for making sound data-driven business decisions until the economy is less volatile. Experian is committed to helping your organization during times of uncertainty. For more resources, visit our Look Ahead 2020 Hub. Learn more

As financial institutions and other organizations scramble to formulate crisis response plans, it’s important to consider the power of data and analytics. Jim Bander, PhD, Experian’s Analytics and Optimization Market Lead discusses the ways that data, analytics and models can help during a crisis. Check out what he had to say: What implications does the global pandemic have on financial institutions’ analytical needs?  JB: COVID-19 is a humanitarian crisis, one that parallels Hurricanes Sandy and Katrina and other natural disasters but which far exceeds their magnitude. It is difficult to predict the impact as huge parts of the global economy have shut down. Another dimension of this disaster is the financial impact: in the US alone, more than 17 million people applied for unemployment in the first 6 weeks of the COVID-19 crisis. That compares to 15 million people in 18 months during the Great Recession. Data and analytics are more important than ever as financial institutions formulate their responses to this crisis. Those institutions need to focus on three key things: safety, soundness, and compliance. Safety: Financial institutions are taking immediate action to mitigate safety risks for their employees and their customers. Soundness: Organizations need to mitigate credit and fraud risk and to evaluate capital and liquidity. Some executives may need a better understanding of how their bank’s stress scenarios were calculated in the past to understand how they must be updated for the future. Important analytic functions include performing portfolio monitoring and benchmarking—quantifying the effects not only of consumer distress, but also of low interest rates. Compliance: Understanding and meeting complex regulatory and compliance requirements is crucial at this time. Companies have to adapt to new credit reporting guidelines. CECL requirements have been relaxed but lenders should assess the effects of COVID, and not only during their annual stress tests. As more consumers seek credit, from an analytics perspective, what considerations should financial institutions make during this time?  JB: During this volatile time, analytics will help financial institutions: Identify financially stressed consumers with early warning indicators Predict future consumer behavior Respond quickly to changes Deliver the best treatments at the right time for individual customers given their specific situations and their specific behavior. Financial institutions should be reevaluating where their organizations have the most vulnerability and should be taking immediate action to mitigate these risks. Some important areas to keep an eye on include early warning indicators, changes in fraudulent behavior (with the increase in digital engagements), and changes in customer behavior. Banks are already offering payment flexibility, deferments, and credit reporting accommodations. If volatility continues or increases, they may need to offer debt forgiveness plans. These organizations should also be prepared to understand their own changing constraints—such as budget, staffing levels, and liquidity requirements— especially as consumers accelerate their move to digital channels. In the near future, lenders should be optimizing their operations, servicing treatments, and lending policies to meet a number of possibly conflicting objectives in the presence of changing constraints and somewhat unpredictable transaction volumes.   What is the smartest next play for financial institutions?  JB: I see our smartest clients doing four things: Adapting to the new normal Maintaining engagement with existing customers by refreshing data that companies have on-hand for these consumers, and obtain additional views of these customers for analytics and data-driven decisioning Reallocating operational resources and anticipating the need for increased capacity in various servicing departments in the future Improving their risk management practices   What is Experian doing to help clients improve their risk management? JB: During this time, banks and other financial institutions are searching for ways to predict consumer behavior, especially during a crisis that combines aspects of a natural disaster with characteristics of a global recession. It is more important than ever to use analytics and optimization. But some of the details of the methodology is different now than during a time of economic expansion. For example, while credit scores (like FICO® and VantageScore® credit scores) will continue to rank consumers in terms of their probability to pay, those scores must be interpreted differently. Furthermore, those scores should be combined with other views of the consumer—such as trends in consumer behavior and with expanded FCRA-compliant data (data that isn’t reported to traditional credit bureaus). One way we’re helping clients improve their credit risk management is to provide them with a list of 140 consumer credit data attributes in 10 categories. With this list, companies will be able to better manage portfolio risk, to better understand consumer behavior, and to select the next best action for each consumer. Four other things we’re doing: We’re quickly updating our loss forecasting and liquidity management offerings to account for new stress scenarios. We’re helping clients review their statistical models’ performance and their customer segmentation practices, and helping to update the models that need refreshing. Our consulting team—Experian Advisory Services—has been meeting with clients virtually--helping them update, execute their crisis and downturn responses, and whiteboard new or updated tactical plans. Last but not least, we’re helping lenders and consumers defend themselves against a variety of fraud and identity theft schemes. Experian is committed to helping your organization during these uncertain times. For more resources, visit our Look Ahead 2020 Hub. Learn more Jim Bander, PhD, Analytics and Optimization Market Lead, Decision Analytics, Experian North America Jim Bander, PhD joined Experian in April 2018 and is responsible for solutions and value propositions applying analytics for financial institutions and other Experian business-to-business clients throughout North America. Jim has over 20 years of analytics, software, engineering and risk management experience across a variety of industries and disciplines. He has applied decision science to many industries including banking, transportation and the public sector. He is a consultant and frequent speaker on topics ranging from artificial intelligence and machine learning to debt management and recession readiness. Prior to joining Experian, he led the Decision Sciences team in the Risk Management department at Toyota Financial Services.