Latest Posts
With the potential annual value of AI and analytics for global banking estimated to reach $1 trillion,1 financial institutions are seeking out efficient ways to implement insights-driven lending. As regulators continue to supervise risk management, lenders must balance the opportunity presented by AI to determine risk more accurately while growing approval rates and reducing the cost of acquisition, with the ability to explain decisions. The challenge of using AI in building credit risk models In a recent study conducted by Forrester Consulting on behalf of Experian, the top pain points for technology decision makers in financial services were reported to be automation and availability of data.2 The implementation of accessible AI solutions in credit risk management allows businesses to improve efficiency and time-to-market metrics by widening data sources, improving automation and decreasing risk. But the implementation of AI and machine learning in credit risk models can pose other challenges. The study also found that 31% of respondents felt that their organization could not clearly explain the reasoning behind credit decisions to customers.2 Although AI has been proven to improve the accuracy of predictive credit risk models, these advancements mean that many organizations need support in understanding and explaining the outcomes of AI-powered decisions to fulfil regulatory obligations, such as the Equal Credit Opportunity Act (ECOA). Moving from traditional model development methodologies to Machine Learning (ML) As lenders move away from traditional parametric models like logistic regression, to ML models like neural nets or tree-based ensemble methods, explainability becomes more complex. Logistic regression has for many years allowed for a clear understanding of the linear relationships between model attributes and the outcome (approval or decline). Once the model is estimated, it is completely explainable. However, ML models are non-parametric, so there are no underlying assumptions made around the distribution (shape) of the sample. Furthermore, the relationships between attributes and outcomes are not assumed to be linear – they’re often non-linear and complex, involving interactions. Such models are perceived to be black boxes where data is consumed as an input, processed and a decision is made without any visibility around the inner dynamics of the model. At the same time, it is possible for ML models to perform better when accurately classifying good customers and those deemed delinquent. Ensuring transparency and explainability is crucial – lenders must be able to identify and explain the most dominant attributes that contribute towards a decision to lend or not. They must also provide ‘reason codes’ at the customer level so any declined applicants can fully understand the main cause and have a path to remediation. The importance of developing transparent and explainable models By prioritizing the development of transparent and interpretable models, financial institutions can also better foster equitable lending practices. However, fair credit decisioning goes beyond the regulatory and ethical obligations - it also makes business sense. Unfair lending leads to higher default rates if creditworthiness is not accurately assessed, therefore increasing bad debts. Removing demographics considered to be the ‘unscored’ or ‘underserved’ (those who are credit worthy but do not have a traditional data trail, but instead a digital footprint comprised of alternative data) can also limit portfolio opportunity for businesses. For these reasons, it is critical to remove or minimize model bias. Bias is an upstream issue that starts at the data collection stage and model algorithm selections. Models developed using logistic regression or machine learning algorithms can be made fairer through carefully selecting attributes relevant to credit decisioning and avoiding sensitive attributes like race, gender, or ethnicity. Wherever sensitive metrics are used, they should be down-weighted to suppress their impact on lending decisions. Some other techniques to mitigate bias include: Thoroughly reviewing the data samples used in modelling. Fair Model Training - Train models using fairness-aware techniques. This may involve adjusting the training process to penalise any discrimination that creeps in. According to Forrester, an essential component of a decisioning platform is one that can “harness the power of AI while enhancing and governing it with well-proven and trusted human business expertise. The best automated decisions come from a combination of both.”3 Developing explainable models goes some way towards reducing bias, but making the decisions explainable to regulatory bodies is a separate issue, and in the digital age of AI, can require deep domain expertise to fulfil. While AI-powered decisioning can help businesses make smarter decisions, they also need the ability to confidently explain their lending practices to stay compliant. With the help of an expert partner, organizations can gain an understanding of what contributed most to a decision and receive detailed and transparent documentation for use with regulators. This ensures lenders can safely grow approval rates, be more inclusive, and better serve their customers. “The solution isn’t simply finding better ways to convey how a system works; rather, it’s about creating tools and processes that can help even the deep expert understand the outcome and then explain it to others.”McKinsey: why businesses need explainable ai and how to deliver it Experian’s Ascend Intelligence ServicesTM Acquire is a custom credit risk model development service that can better quantify risk, score more applicants, increase automation, and drive more profitable decisions. Find out more Confidently explain lending practices:Detailed, rigorous, and transparent documentation that has been proven to meet the strictest regulatory standards. Breaking Machine Learning (ML) out of the black box:Understand what contributed most to a decision and generate adverse action codes directly from the model through our patent-pending ML explainability.References: "The executive's AI playbook," McKinsey.com. (See "Banking," under "Value & Assess.") In a study conducted by Forrester Consulting on behalf of Experian, we surveyed 660 and interviewed 60 decision makers for technology purchases that support the credit lifecycle at their financial services organisation. The study included businesses across North America, UK and Ireland, and Brazil. 2023_05_Forrester_AI-Decisioning-Platforms-Wave.pdf https://www.mckinsey.com/capabilities/quantumblack/our-insights/why-businesses-need-explainable-ai-and-how-to-deliver-it Contributors:Masood Akhtar, Global Product Marketing Manager
As the lines between authentic and synthetic blur more than ever before, we explore four fraud trends likely to be influenced the most by GEN AI technology in 2024 and what businesses can do to prevent them.
Lenders are using automation across the credit lifecycle and intend to invest further in the next 12 months. We look at the use cases for automation and address the key challenges lenders face when automating decisions.
Authorised Push Payment fraud is growing, and as regulators begin to take action around the world to try to tackle it, we look at what financial institutions need to focus on now.
We take a look at five transformative use cases in lending, and organisational priorities for integrating Gen AI into customer lifecycle processes.
We asked lenders how much Gen AI plays a role in their credit customer lifecycle processes and what Gen AI adoption looks like for them
Fraud prevention is a critical concern for businesses today. To help combat this ever-present threat, the consortium approach has emerged as a powerful tool in the fight against fraud. By pooling resources, expertise, and creating visibility, consortium members can be more effective in detecting and preventing fraudulent activities.
With an ever-growing number of data sources, businesses must be able to rapidly access and integrate them into decisioning processes using no-code tools to stay ahead of the competition.
Liminal, a leading market intelligence firm recently recognized Experian as a market leader for compliance and fraud prevention capabilities and execution in its Liminal Link Index on Account Opening in Financial Services.
In today's fast-paced digital landscape, businesses are inundated with an unprecedented amount of data and information. Making informed decisions with the data quickly and effectively has become a crucial factor for success. Enter digital decisioning—a transformative approach that harnesses the power of data, analytics, and automation to drive reliable and expedited decision-making. This article delves into the world of digital decisioning, exploring its significance, components, and benefits. The Essence of Digital Decisioning At its core, digital decisioning is the process of leveraging software solutions that use digital decisioning platforms or custom-built engines to author decision logic; use decision intelligence technologies such as machine learning and AI; use digital decisions in vertical and horizontal use cases; and manage the full decision logic lifecycle, including feedback loops, to continuously improve decision logic. It enables organizations to make well-informed choices by automating and optimizing complex decision processes. By amalgamating data from various sources in real-time, including credit data, user behavior, market trends, historical data, and external factors, digital decisioning ensures that timely decisions are not only data-driven but also contextually relevant. Components of Digital Decisioning Continuous Data Feed: This is the lifeblood of digital decisions. Organizations normalize data from disparate sources to form comprehensive and accurate datasets. Customer data might include income, credit history, transactional data, bill payment, or digital footprint data; however, regardless of the sources, it’s critical that data is coalesced into a single, virtualized view. Advanced Analytics and Machine Learning: Analytics and machine learning algorithms are deployed to extract meaningful insights from the collected data. These insights are used to model decision scenarios, predict outcomes, and uncover hidden patterns. Decision Models: Decision models are created based on the insights derived from data analysis. These models define the rules and logic for making decisions, incorporating factors such as risk tolerance, business goals, and regulatory compliance. Direct Feedback Loop: Every decision has an outcome. For example, an automated loan offer is either accepted or declined by the customer. These outcomes — good and bad — automatically feed into the decisioning model, which enables the machine learning technology to “learn” which decisions are optimal, given the circumstances and customer profile. This enables the model to adapt and grow more accurately and precisely over time. Automation: Automation engines execute the decision models in real time, allowing for rapid and consistent decision-making without human intervention. This enhances efficiency and minimizes the risk of errors. According to a 2022 Gartner poll, the CIO Agenda, more than 80% of companies plan to keep or grow their investment in automation solutions. Benefits of Digital Decisioning Enhanced Accuracy: Digital decisioning eliminates human biases and inconsistencies, resulting in more accurate and objective decisions. Improved Efficiency: Automation reduces decision-making time from hours or days to milliseconds, enabling organizations to respond swiftly to market changes and customer demands. Hyper Personalization: By considering individual preferences, behaviors, and history, digital decisioning facilitates the creation of tailored experiences for customers, leading to higher satisfaction and engagement. Scalability: The automated nature of digital decisioning ensures that it can handle a high volume of decisions seamlessly, making it ideal for businesses experiencing rapid growth. Regulatory Compliance: Explainable decision models can be designed to incorporate regulatory guidelines and compliance requirements, reducing the risk of legal complications. Use Case: Respond faster to credit card applications and personalize cross-sell offers Customers apply online for a credit card from a bank. As they’re being pre-qualified, digital decisioning will instantly analyze the customers’ accounts with the bank including disclosed and undisclosed cash flow. A digital decisioning software solution enables the bank to assess risk exposure and anticipate the customer’s immediate need(s), thereby automating the application assessment and approval steps to reduce approval times from weeks to minutes. Based on the bank’s comprehensive understanding of that customer at that moment, it triggers a personalized cross-sell offer for another relevant financial product, automatically boosting incremental revenue. Conclusion Digital decisioning marks a pivotal advancement in how choices are made in business. By harnessing the power of data, analytics, and automation, organizations can make faster, more accurate decisions that are aligned with their goals and market realities. As this technology continues to evolve, it will reshape industries and empower individuals to navigate the complex digital landscape with confidence. Experian’s decisioning management platform allows clients to operationalize the power of rich data, advanced analytics, and automated decisioning software to support the customer lifecycle. Its key differentiators include credit risk, fraud risk, and strategy expertise, fast deployment of strategies into test and production, empowerment of business users, and proactive monitoring of strategy performance by users. Its key use cases include reducing acquisition costs, credit risk, and fraud risk, and improving acceptance rate and the customer journey. Experian has been named a Technology Leader in the August 2023 SPARK Matrix on Digital Decisioning Platforms report published by Quadrant Knowledge Solutions. The report highlights the growth of decisioning platforms and the changing market trends that are driving adoption, including the role machine learning and AI are playing in the technology market. This placement is proof that Experian offers best-in-class capabilities through market-leading data, orchestration and automation, advanced analytical models, decision performance, and reporting. Our cloud-based infrastructure enables a scalable and modular platform that allows our solutions to be suitable for customers of all sizes. Read the report Experian’s Decisioning Management Platform: Accelerating analytics, decisioning, and fraud detection automation Continuous improvement loop: Advanced machine learning models improve decisioning quality
As economic uncertainty continues to loom, the threat of fraud continues to grow and is becoming more sophisticated. It’s only going to get worse. Due to intensifying inflationary pressures, prices and costs have been increasing which has led to financial hardship impacting individuals and businesses. This provides an opportunity and motive for bad actors to figure out new ways to commit fraud. Federal Trade Commission data shows that consumers reported losing nearly $8.8 billion to fraud in 2022, an increase of more than 30 percent over the previous year. PwC’s Global Economic Crime and Fraud Survey 2022 shows 51% of surveyed organisations say they experienced fraud in the past two years, the highest level in their 20 years of research. Additional investments in fraud prevention technology are a priority for businesses to combat these evolving threats, according to Experian's Sept. 2022 Global Insights report, which states that 94% of businesses report it as the top priority. Since fraud is becoming more sophisticated, part of the challenge that businesses face is to constantly evaluate multiple solutions so that they can continuously improve their fraud detection and prevention capabilities. Investments that can deliver the highest ROI are the solutions that are integrated and orchestrated in a comprehensive fraud reduction intelligence platform. This gives businesses the flexibility to manage evolving strategies and mitigate threats with real-time decisioning. Experian’s CrossCore is an integrated digital identity and fraud risk platform. It offers global solutions to help protect businesses from fraud and maintain compliance with regulatory requirements, using real-time risk analytics and decision-making strategies. The platform aggregates various fraud and identity verification sources to consolidate risk and trust decisions for Experian clients throughout the consumer journey. Experian’s CrossCore has been recognized as an Overall Leader, Innovation Leader, Product Leader, and Market Leader in KuppingerCole’s Fraud Reduction Intelligence Platform Leadership Compass 2023. This recognition highlights Experian's comprehensive approach to combating fraud. It validates that CrossCore offers best-in-class capabilities by augmenting Experian’s industry-leading identity and fraud offerings with a highly curated ecosystem of partners which enables further optionality for our clients based on their specific needs. Read the report CrossCore's Capabilities
A changing economic landscape needs a new approach. The new digital consumer is here to stay and they expect businesses to support them with the products and services they need to navigate the rising cost of living, in a secure digital world personalized to them.





