Tag: credit risk models

Article written by Alex Lintner, Experian's Group President of Consumer Information Services and Sandy Anderson, Experian's Senior Vice President of Client and Sales Operations Many consumers are facing financial stress due to unemployment and other hardships related to the COVID-19 pandemic. Not surprisingly, data scientists at Experian are looking into how consumers’ credit scores may be impacted during the COVID-19 national emergency period as financial institutions and credit bureaus follow guidance from financial regulators and law established in Section 4021 of the Coronavirus Aid, Relief, and Economic Security Act (CARES Act). In a nutshell, Experian finds that if consumers contact their lenders and are granted an accommodation, such as a payment holiday or forbearance, and lenders report the accommodation accordingly, consumer scores will not be materially affected negatively. It’s not just Experian’s findings, but also those of the major credit scoring companies, FICO® and VantageScore®. FICO has reported that if a lender provides an accommodation and payments are reported on time consistent with the CARES Act, consumers will not be negatively impacted by late payments related to COVID-19. VantageScore® has also addressed this issue and stated that its models are designed to mitigate the impact of missed payments from COVID-19. At the same time, if as predicted, lenders tighten underwriting standards following 11 consecutive years of economic growth, access to credit for some consumers may be curtailed notwithstanding their score because their ability to repay the loan may be diminished. Regulatory guidance and law provide a robust response Recently, the Federal Reserve, along with the federal and state banking regulators, issued a statement encouraging mortgage servicers to work with struggling homeowners affected by the COVID-19 national emergency by allowing borrowers to defer mortgage payments up to 180-days or longer. The Federal Deposit Insurance Corporation stated that financial institutions should “take prudent steps to assist customers and communities affected by COVID-19.” The Office of the Comptroller of the Currency, which regulates nationally chartered banks, encouraged banks to offer consumers payment accommodations to avoid delinquencies and negative credit bureau reporting. This regulatory guidance was backed by Congress in passing the CARES Act, which requires any payment accommodations to be reported to a credit bureau as “current.” The Consumer Financial Protection Bureau, which has oversight of all financial service providers, reinforced the regulatory obligation in the CARES Act. In a statement, the Bureau said “the continuation of reporting such accurate payment information produces substantial benefits for consumers, users of consumer reports and the economy as a whole.” Moreover, the consumer reporting industry has a history of successful coordination during emergency circumstances, like COVID-19, and we’ve provided the support necessary for lenders to report accurately and consistent with regulatory guidance. For example, when a consumer faces hardship, a lender can add a code that indicates a customer or borrower has been “affected by natural or declared disaster.” If a lender uses this or a similar code, a notification about the disaster or other event will appear in the credit report with the trade line for the customer’s account and will remain on the trade line until the lender removes it. As a result, the presence of the code will not negatively impact the consumer credit score. However, other factors may impact a consumer’s score, such as an increase in a consumer’s utilization of their credit lines, which is a likely scenario during a period of financial stress. Suppression or Deletion of late payments will hurt, not help, credit scores In response to the nationwide impact of COVID-19, some lawmakers have suggested that lenders should not report missed payments or that credit bureaus should delete them. The presumption is that these actions would hold consumers harmless during the crisis caused by this pandemic. However, these good intentions end up having a detrimental impact on the whole credit ecosystem as consumer credit information is no longer accurately reflecting consumers’ specific situation. This makes it difficult for lenders to assess risk and for consumers to obtain appropriately priced credit. Ultimately, the best way to help is a consumer-specific solution, meaning one in which a lender reaches an accommodation with each affected individual, and accurately reflects that person’s unique situation when reporting to credit bureaus. When a consumer misses a payment, the information doesn’t end up on a credit report immediately. Most payments are monthly, so a consumer’s payment history with a financial institution is updated on a similar timeline. If, for example, a lender was required to suppress reporting for three months during the COVID-19 national emergency, the result would be no data flowing onto a credit report for three months. A credit report would therefore show monthly payments and then three months of no updates. The same would be true if a credit reporting agency were required to suppress or delete payment information. The lack of data, due to suppression or deletion, means that lenders would be blinded when making credit decisions, for example to increase a credit limit to an existing customer or to grant a new line of credit to a prospective customer. When faced with a blind spot, and unable to assess the real risk of a consumer’s credit history, the prudential tendency would be to raise the cost of credit, or to decrease the availability of credit, to cover the risk that cannot be measured. This could effectively end granting of credit to new customers, further stifling economic recovery and consumer financial health at a time when it’s needed most. Beyond the direct impact on consumers, suppression or deletion of credit information could directly affect the safety and soundness of the nation’s consumer and small business lending system. With missing data, lenders and their regulators would be flying blind as to the accurate information about a consumer’s risk and could result in unknowingly holding loan portfolios with heightened risk for loss. Too many unexpected losses threaten the balance of the financial system and could further seize credit markets. Experian is committed to helping consumers manage their credit and working with lenders on how best to report consumer-specific solutions. To learn more about what consumers can do to manage credit during the COVID-19 national emergency, we’ve provided resources on our website. For individuals looking to explore options their lenders may offer, we’ve included links to many of the companies and update them continuously. With good public policy and consumer-specific solutions, consumers can continue to build credit and help our economy grow.  

From a capricious economic environment to increased competition from new market entrants and a customer base that expects a seamless, customized experience, there are a host of evolving factors that are changing the way financial institutions operate. Now more than ever, financial institutions are turning to their data for insights into their customers and market opportunities. But to be effective, this data must be accurate and fresh; otherwise, the resulting strategies and decisions become stale and less effective. This was the challenge facing OneMain Financial, a large provider of personal installment loans serving 10 million total customers across more than 1,700 branches—creating accurate, timely and robust insights, models and strategies to manage their credit portfolios. Traditionally, the archive process had been an expensive, time-consuming, and labor-intensive process; it can take months from start to finish. OneMain Financial needed a solution to reduce expenses and the time involved in order to improve their core risk modeling.   In this recent IDC Customer Spotlight, sponsored by Experian, "Improving Core Risk Modeling with Better Data Analysis," Steven D’Alfonso, Research Director spoke with the Senior Managing Director and head of model development at OneMain Financial who turned to Experian’s Ascend Analytical Sandbox to improve its core risk modeling through reject inferencing. But OneMain Financial also realized additional benefits and opportunities with the solution including compliance and economic stress testing. Read the customer spotlight to learn more about the explore how OneMain Financial: Reduced expense and effort associated with its archive process Improved risk model development timing from several months to 1-2 weeks Used Sandbox to gain additional market insight including: market share, benchmarking and trends, etc. Read the Case Study

I believe it was George Bernard Shaw that once said something along the lines of, “If economists were laid end-to-end, they’d never come to a conclusion, at least not the same conclusion.” It often feels the same way when it comes to big data analytics around customer behavior. As you look at new tools to put your customer insights to work for your enterprise, you likely have questions coming from across your organization. Models always seem to take forever to develop, how sure are we that the results are still accurate? What data did we use in this analysis; do we need to worry about compliance or security? To answer these questions and in an effort to best utilize customer data, the most forward-thinking financial institutions are turning to analytical environments, or sandboxes, to solve their big data problems. But what functionality is right for your financial institution? In your search for a sandbox solution to solve the business problem of big data, make sure you keep these top four features in mind. Efficiency: Building an internal data archive with effective business intelligence tools is expensive, time-consuming and resource-intensive. That’s why investing in a sandbox makes the most sense when it comes to drawing the value out of your customer data.By providing immediate access to the data environment at all times, the best systems can reduce the time from data input to decision by at least 30%. Another way the right sandbox can help you achieve operational efficiencies is by direct integration with your production environment. Pretty charts and graphs are great and can be very insightful, but the best sandbox goes beyond just business intelligence and should allow you to immediately put models into action. Scalability and Flexibility: In implementing any new software system, scalability and flexibility are key when it comes to integration into your native systems and the system’s capabilities. This is even more imperative when implementing an enterprise-wide tool like an analytical sandbox. Look for systems that offer a hosted, cloud-based environment, like Amazon Web Services, that ensures operational redundancy, as well as browser-based access and system availability.The right sandbox will leverage a scalable software framework for efficient processing. It should also be programming language agnostic, allowing for use of all industry-standard programming languages and analytics tools like SAS, R Studio, H2O, Python, Hue and Tableau. Moreover, you shouldn’t have to pay for software suites that your analytics teams aren’t going to use. Support: Whether you have an entire analytics department at your disposal or a lean, start-up style team, you’re going to want the highest level of support when it comes to onboarding, implementation and operational success. The best sandbox solution for your company will have a robust support model in place to ensure client success. Look for solutions that offer hands-on instruction, flexible online or in-person training and analytical support. Look for solutions and data partners that also offer the consultative help of industry experts when your company needs it. Data, Data and More Data: Any analytical environment is only as good as the data you put into it. It should, of course, include your own client data. However, relying exclusively on your own data can lead to incomplete analysis, missed opportunities and reduced impact. When choosing a sandbox solution, pick a system that will include the most local, regional and national credit data, in addition to alternative data and commercial data assets, on top of your own data.The optimum solutions will have years of full-file, archived tradeline data, along with attributes and models for the most robust results. Be sure your data partner has accounted for opt-outs, excludes data precluded by legal or regulatory restrictions and also anonymizes data files when linking your customer data. Data accuracy is also imperative here. Choose a big data partner who is constantly monitoring and correcting discrepancies in customer files across all bureaus. The best partners will have data accuracy rates at or above 99.9%. Solving the business problem around your big data can be a daunting task. However, investing in analytical environments or sandboxes can offer a solution. Finding the right solution and data partner are critical to your success. As you begin your search for the best sandbox for you, be sure to look for solutions that are the right combination of operational efficiency, flexibility and support all combined with the most robust national data, along with your own customer data. Are you interested in learning how companies are using sandboxes to make it easier, faster and more cost-effective to drive actionable insights from their data? Join us for this upcoming webinar. Register for the Webinar

Machine learning (ML), the newest buzzword, has swept into the lexicon and captured the interest of us all. Its recent, widespread popularity has stemmed mainly from the consumer perspective. Whether it’s virtual assistants, self-driving cars or romantic matchmaking, ML has rapidly positioned itself into the mainstream. Though ML may appear to be a new technology, its use in commercial applications has been around for some time. In fact, many of the data scientists and statisticians at Experian are considered pioneers in the field of ML, going back decades. Our team has developed numerous products and processes leveraging ML, from our world-class consumer fraud and ID protection to producing credit data products like our Trended 3DTM attributes. In fact, we were just highlighted in the Wall Street Journal for how we’re using machine learning to improve our internal IT performance. ML’s ability to consume vast amounts of data to uncover patterns and deliver results that are not humanly possible otherwise is what makes it unique and applicable to so many fields. This predictive power has now sparked interest in the credit risk industry. Unlike fraud detection, where ML is well-established and used extensively, credit risk modeling has until recently taken a cautionary approach to adopting newer ML algorithms. Because of regulatory scrutiny and perceived lack of transparency, ML hasn’t experienced the broad acceptance as some of credit risk modeling’s more utilized applications. When it comes to credit risk models, delivering the most predictive score is not the only consideration for a model’s viability. Modelers must be able to explain and detail the model’s logic, or its “thought process,” for calculating the final score. This means taking steps to ensure the model’s compliance with the Equal Credit Opportunity Act, which forbids discriminatory lending practices. Federal laws also require adverse action responses to be sent by the lender if a consumer’s credit application has been declined. This requires the model must be able to highlight the top reasons for a less than optimal score. And so, while ML may be able to deliver the best predictive accuracy, its ability to explain how the results are generated has always been a concern. ML has been stigmatized as a “black box,” where data mysteriously gets transformed into the final predictions without a clear explanation of how. However, this is changing. Depending on the ML algorithm applied to credit risk modeling, we’ve found risk models can offer the same transparency as more traditional methods such as logistic regression. For example, gradient boosting machines (GBMs) are designed as a predictive model built from a sequence of several decision tree submodels. The very nature of GBMs’ decision tree design allows statisticians to explain the logic behind the model’s predictive behavior. We believe model governance teams and regulators in the United States may become comfortable with this approach more quickly than with deep learning or neural network algorithms. Since GBMs are represented as sets of decision trees that can be explained, while neural networks are represented as long sets of cryptic numbers that are much harder to document, manage and understand. In future blog posts, we’ll discuss the GBM algorithm in more detail and how we’re using its predictability and transparency to maximize credit risk decisioning for our clients.