Test

Developing machine learning (ML) credit risk models can be more challenging than traditional credit risk modeling approaches. But once deployed, ML models can increase automation and expand a lender’s credit universe.  For example, by using ML-driven credit risk models and combining traditional credit data with transactional bank data, a type of alternative credit data* , some lenders see a Gini uplift of 60 to 70 percent compared to a traditional credit risk model.1   New approaches to model operations are also helping lenders accelerate their machine learning model development processes and go from collecting data to deploying a new model in days instead of months.  READ MORE: Getting AI-driven decisioning right in financial services What is machine learning model development? Machine learning model development is what happens before the model gets deployed. It's often broken down into several steps. Define the problem: If you’re building an ML credit risk model, the problem you may be trying to solve is anticipating defaults, improving affordability for borrowers or expanding your lending universe by scoring more thin-file and previously unscorable consumers.  Gather, clean and stage data: Identify helpful data sources, such as internal, credit bureau and alternative credit data. The data will then need to be consolidated, structured, labeled and categorized. Machine learning can be useful here as well, as ML models can be trained to label and categorize raw data. Feature engineering: The data is then analyzed to identify the individual variables and clusters of variables that may offer the most lift. Features that may directly or unintentionally create bias should be removed or limited.  Create the model: Deciding which algorithms and techniques to use when developing a model can be part art and part science. Because lenders need to be able to explain the decisions they make to consumers and regulators, many lenders build model explainability into new ML-driven credit risk models. Validate and deploy: New models are validated and rigorously tested, often as challengers to the existing champion model. If the new model can consistently outperform, it may move on to production.  The work doesn’t stop once a model is live — it needs to be continuously monitored for drift, and potentially recalibrated or replaced with a new model. About 10 percent of lenders use tools to automatically alert them when their models start to drift. But around half make a point of checking deployed models for drift every month or quarter.3  READ MORE: Journey of an ML Model What is model deployment? Model deployment is one of the final steps in the model lifecycle — it’s when you move the model from development and validation to live production.  New models can be deployed in various ways, including via API integration and cloud service deployment using public, private or hybrid architecture. However, integrating a new model with existing systems can be challenging. About a third (33 percent) of consumer lending organizations surveyed in 2023 said it took them one to two months for model deployment-related activities. A little less (29 percent) said it took them three to six months.  Overall, it often takes up to 15 months for the entire development to deployment process — and 55 percent of lenders report building models that never get deployed.2  READ MORE: Accelerating the Model Development and Deployment Lifecycle Benefits of deploying machine learning credit risk models Developing, deploying, monitoring and recalibrating ML models can be difficult and costly. But financial institutions have a lot to gain from embracing the future of underwriting. Improve credit risk assessment: ML-driven models can incorporate more data sources and more precisely assess credit risk to help lenders price credit offers and decrease charge-offs.  Expand automation: More precise scoring can also increase automation by reducing how many applications need to go to manual review.  Increase financial inclusion: ML-models may be able to evaluate consumers who don’t have recent credit information or thick enough credit files to be scorable by traditional models. In short, ML models can help lenders make better loan offers to more people while taking on less risk and using fewer internal resources to review applications.  CASE STUDY: Atlas Credit, a small-dollar lender, partnered with Experian® to develop a fully explainable machine learning credit risk model that incorporated internal data, trended data, alternative financial services data and Experian’s attributes. Atlas Credit can use the new model to make instant decisions and is expected to double its approvals while decreasing losses by up to 20 percent.  How we can help Experian offers many machine learning solutions for different industries and use cases via the Experian Ascend Technology Platform™. For example, with Ascend ML Builder™, lenders can access an on-demand development environment that can increase model velocity — the time it takes to complete a new model’s lifecycle. You can configure Ascend ML Builder based on the compute you allocate and your use cases, and the included code templates (called Accelerators) can help with data wrangling, analysis and modeling.  There’s also Ascend Ops™, a cloud-based model operations solution. You can use Ascend Ops to register, test and deploy custom features and models. Automated model monitoring and management can also help you track feature and model data drift and model performance to improve models in production. Learn more about our machine learning and model deployment solutions *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. 1. Experian (2023). Raising the AI Bar 2. Experian (2023). Accelerating Model Velocity in Financial Institutions 3. Ibid.

It's 2024, and it has never been easier to buy a car in person or online, but automobiles are not quite as affordable as prior to the pandemic. While everyone is looking for the best car deal, some folks are pushing it too far and are falling for auto scams. What is auto lending fraud? Fraud perpetrators are drawn to sectors they perceive as highly lucrative. The accessibility of online vehicle financing and purchasing, coupled with the substantial financial magnitude associated with automotive transactions, renders the auto industry an optimal avenue for cash-out endeavors. Auto lending fraud refers to deceptive or fraudulent activities related to obtaining or processing auto finance. This can involve various schemes aimed at misleading lenders, financial institutions, or individuals involved in the lending process. Criminal networks now operate on social media sites like Facebook and Telegram, offering a unique car buying service using synthetic identities. They create synthetic identities, finance cars with no down payment, and deliver vehicles to addresses chosen by buyers. The process involves selecting a car online, sending a small amount of dollars and a photo against a white background, and receiving a fake driver's license. Those networks claim to exploit car sites' policies successfully. While appealing to those in urgent need of a car, the service poses significant risks as the synthetic identity may be used for other fraudulent activities beyond car purchase. Who is at risk? Everyone involved in the car buying process is at risk of falling victim to auto loan fraud. Car buyers looking to secure financing, as well as lenders, need to be aware of the potential red flags and take necessary precautions to safeguard their interests. Thieves leverage the internet and electronic transactions to perpetrate auto loan fraud. While the growth of online commerce has improved many aspects of trade, it has also made personally identifiable information and financial details vulnerable to data breaches. Unscrupulous individuals can gain unauthorized access to such information, providing the foundation for various identity theft schemes. The internet also facilitates the creation of seemingly legitimate documents that support auto loan fraud. Online services exist to help fraudsters fabricate income statements and fake employment verification from fictitious companies. This trend has made auto loan fraud an increasingly popular method for acquiring vehicles with minimal cash and risk. Another auto loan fraud trend is the increased use of CPN (Credit Privacy Number). Credit Repair firms introduced a novel strategy targeting consumers — the CPN (Credit Privacy Number). Marketed as a nine-digit alternative to a Social Security Number (SSN), CPNs are purportedly usable for obtaining credit. However, it is crucial to note that utilizing a CPN for credit applications constitutes a criminal offense, potentially leading to legal consequences, and car dealerships should not accept them.  Detecting auto loan fraud There are several types of auto loan fraud worth noting to better understand the landscape: Income fabrication: Prospective buyers may falsify their income details to qualify for a larger loan or better terms. Lenders should verify income using documents like pay stubs, tax returns, or bank statements and watch out for inconsistencies. Employment misrepresentation: Applicants could lie about their job titles or employment status. Lenders should verify employment details through HR departments or by directly contacting the employer. Trade-in vehicle deception: Some individuals may overstate the value of their trade-in vehicle to secure a higher loan amount. Lenders should perform thorough appraisals or consult trusted sources to ascertain the accurate value of the trade-in. Identity fraud: Fraudsters can assume someone else's identity, commit first party fraud or create a fictitious persona to obtain an auto loan. Lenders must verify the applicant's identity using reliable identification documents and consider using identity verification tools. Forged documentation: Fraudsters may forge or alter documents like income statements, bank statements, or driver's licenses. Lenders should scrutinize documents carefully for discrepancies or signs of tampering. Straw borrower fraud: In this scenario, someone with poor credit convinces a friend or relative with better credit to front the deal, posing as the buyer. A better credit score allows for better terms or a more valuable vehicle. The actual buyer may continue to make payments to the friend, or the loan may become delinquent, negatively affecting the friend's credit score. In extreme cases, the straw buyer is part of a fraud ring, and the vehicle has already been sold in a foreign market. Synthetic identity fraud: Data breaches providing personally identifying information enable identity theft schemes. Perpetrators use illicitly acquired information to create false borrower profiles that appear authentic. These profiles typically have excellent credit, a social security number, an affluent home address, stable employment, and other attributes that make them seem like desirable borrowers. However, a detailed investigation reveals subtle inconsistencies indicative of high risk. How to prevent auto loan fraud To combat auto loan fraud and protect profitability, auto lenders can leverage technological advancements. By applying analytics and machine learning to millions of loan applications and histories, you can identify fraudulent patterns and inconsistencies. Machine learning can determine the type of suspected fraud and provide a confidence factor to guide further investigation and verification. Additionally, you should: Conduct thorough background checks on prospective buyers and verify their personal information and documents. and verify their personal information and documents. Implement a comprehensive loan underwriting process that includes income verification, employment verification, and collateral evaluation. Educate employees about common fraud schemes, warning signs, and best practices to ensure they remain vigilant during loan applications. Foster a culture of cooperation with local law enforcement agencies, sharing information about suspected fraudsters to help prevent future incidents. It is important for individuals and businesses to be vigilant and report any suspicious activity. Car dealerships and financial institutions work to prevent fraud through proper identification verification, credit checks, and adherence to legal and ethical standards. If you suspect fraudulent activity or identity theft, it is crucial to report it to the appropriate authorities immediately. Gearing-up Taking advantage of the latest fintech capabilities, such as cloud-based loan origination that integrates analytics, machine learning, and automated verification services, can significantly reduce the likelihood of fraudulent applications becoming another auto lending fraud statistic. By combining the best data with our automated ID verification checks, Experian helps you safeguard your business and onboard customers efficiently. Our best-in-class solutions employ device recognition, behavioral biometrics, machine learning, and global fraud databases to spot and block suspicious activity before it becomes a problem. Learn more about our automotive fraud prevention solutions *This article includes content created by an AI language model and is intended to provide general information.

Our Econ to Action podcast series dives into the top economic trends and the implications of those trends in the market. In each episode, we explore the challenges different market segments are facing and how businesses in the segment are navigating the current economic climate. Listen to our host, Josee Farmer, Economic Analyst, discuss these topics with other Experian experts. In a special episode of Econ to Action to commemorate the start of the new year, Josee is joined by three market experts to discuss the 2024 forecast. The experts discuss the broader U.S. economic forecast, according to the Federal Reserve’s SEP (Summary of Economic Projections), as well as the forecasts for the mortgage, collections and national bank market segments. Shawn Rife, Client Executive, returns to Econ to Action with more collections insights, along with new guests Kendall Hellman, Senior Account Executive, Strategic Sales and Rob Rollo, Senior Account Executive, Strategic Mortgage Sales. Watch our first video episode and learn how the 2024 forecast will affect the market. Be sure to go back and catch up on previous episodes on our Econ to Action podcast hub and visit Experian Edge for our latest economic, credit and market insights.