Tag: credit model

Here are the four steps fintechs should take to reenter the lending market intelligently, while mitigating as much risk as possible.

Financial institutions preparing for the launch of the Financial Accounting Standard Board’s (FASB) new current expected credit loss model, or CECL, may have concerns when it comes to preparedness, implications and overall impact. Gavin Harding, Experian’s Senior Business Consultant and Jose Tagunicar, Director of Product Management, tackled some of the tough questions posed by the new accounting standard. Check out what they had to say: Q: How can financial institutions begin the CECL transition process? JT: To prepare for the CECL transition process, companies should conduct an operational readiness review, which includes: Analyzing your data for existing gaps. Determining important milestones and preparing for implementation with a detailed roadmap. Running different loss methods to compare results. Once losses are calculated, you’ll want to select the best methodology based on your portfolio. Q: What is required to comply with CECL? GH: Complying with CECL may require financial institutions to gather, store and calculate more data than before. To satisfy CECL requirements, financial institutions will need to focus on end-to-end management, determine estimation approaches that will produce reasonable and supportable forecasts and automate their technology and platforms. Additionally, well-documented CECL estimations will require integrated workflows and incremental governance. Q: What should organizations look for in a partner that assists in measuring expected credit losses under CECL? GH: It’s expected that many financial institutions will use third-party vendors to help them implement CECL. Third-party solutions can help institutions prepare for the organization and operation implications by developing an effective data strategy plan and quantifying the impact of various forecasted conditions. The right third-party partner will deliver an integrated framework that empowers clients to optimize their data, enhance their modeling expertise and ensure policies and procedures supporting model governance are regulatory compliant. Q: What is CECL’s impact on financial institutions? How does the impact for credit unions/smaller lenders differ (if at all)? GH: CECL will have a significant effect on financial institutions’ accounting, modeling and forecasting. It also heavily impacts their allowance for credit losses and financial statements. Financial institutions must educate their investors and shareholders about how CECL-driven disclosure and reporting changes could potentially alter their bottom line. CECL’s requirements entail data that most credit unions and smaller lenders haven’t been actively storing and saving, leaving them with historical data that may not have been recorded or will be inaccessible when it’s needed for a CECL calculation. Q: How can Experian help with CECL compliance? JT: At Experian, we have one simple goal in mind when it comes to CECL compliance: how can we make it easier for our clients? Our Ascend CECL ForecasterTM, in partnership with Oliver Wyman, allows our clients to create CECL forecasts in a fraction of the time it normally takes, using a simple, configurable application that accurately predicts expected losses. The Ascend CECL Forecaster enables you to: Fulfill data requirements: We don’t ask you to gather, prepare or submit any data. The application is comprised of Experian’s extensive historical data, delivered via the Ascend Technology PlatformTM, economic data from Oxford Economics, as well as the auto and home valuation data needed to generate CECL forecasts for each unsecured and secured lending product in your portfolio. Leverage innovative technology: The application uses advanced machine learning models built on 15 years of industry-leading credit data using high-quality Oliver Wyman loan level models. Simplify processes: One of the biggest challenges our clients face is the amount of time and analytical effort it takes to create one CECL forecast, much less several that can be compared for optimal results. With the Ascend CECL Forecaster, creating a forecast is a simple process that can be delivered quickly and accurately. Q: What are immediate next steps? JT: As mentioned, complying with CECL may require you to gather, store and calculate more data than before. Therefore, it’s important that companies act now to better prepare. Immediate next steps include: Establishing your loss forecast methodology: CECL will require a new methodology, making it essential to take advantage of advanced statistical techniques and third-party solutions. Making additional reserves available: It’s imperative to understand how CECL impacts both revenue and profit. According to some estimates, banks will need to increase their reserves by up to 50% to comply with CECL requirements. Preparing your board and investors: Make sure key stakeholders are aware of the potential costs and profit impacts that these changes will have on your bottom line. Speak with an expert

Machine learning's ability to consume vast amounts of data to uncover patterns and deliver results makes it well suited for the credit risk industry

The phrase swap set refers to “swapping out” a set of customer accounts and replacing them with, or “swapping in,” a set of good customer accounts.

By: Kari Michel Credit risk models are used by almost every lender, and there are many choices to choose from including custom or generic models.  With so many choices how do you know what is best for your portfolio?  Custom models provide the strongest risk prediction and are developed using an organization’s own data.  For many organizations, custom models may not be an option due to the size of the portfolio (may be too small), lack of data including not enough bads, time constraints, and/or lack of resources. If a custom model is not an option for your organization, generic bureau scoring models are a very powerful alternative for predicting risk.  But how can you understand if your current scoring model is the best option for you? You may be using a generic model today and you hear about a new generic model, for example the VantageScore® credit score.   How do you determine if the new model is more predictive than your current model for your portfolio?  The best way to understand if the new model is more predictive is to do a head-to-head comparison – a validation.  A validation requires a sample of accounts from your portfolio including performance flags.  An archive is pulled from the credit reporting agency and both scores are calculated from the same time period and a performance chart is created to show the comparison. There are two key performance metrics that are used to determine the strength of the model.  The KS (Komogorov-Smirnov) is a statistical term that measures the maximum difference between the bad and good cumulative score distribution.  The KS range is from 0% to 100%, with the higher the KS the stronger the model.  The second measurement uses the bad capture rate in the bottom 5%, 10% or 15% of the score range. A stronger model will provide better risk prediction and allow an organization to make better risk decisions.  Overall, when stronger scoring models are used, organizations will be best prepared to decrease their bad rates and have a more profitable portfolio.  

By: Tracy Bremmer In our last blog (July 30), we covered the first three stages of model development which are necessary whether developing a custom or generic model.  We will now discuss the next three stages, beginning with the “baking” stage:  scorecard development. Scorecard development begins as segmentation analysis is taking place and any reject inference (if needed) is put into place. Considerations for scorecard development are whether the model will be binned (divides predictive attributes into intervals) or continuous (variable is modeled in its entirety), how to account for missing values (or “false zeros”), how to evaluate the validation sample (hold-out sample vs. an out-of-time sample), avoidance of over-fitting the model, and finally what statistics will be used to measure scorecard performance (KS, Gini coefficient, divergence, etc.). Many times lenders assume that once the scorecard is developed, the work is done.   However, the remaining two steps are critical to development and application of a predictive model:  implementation/documentation and scorecard monitoring.   Neglecting these two steps is like baking a cake but never taking a bite to make sure it tastes good. Implementation and documentation is the last stage in developing a model that can be put to use for enhanced decisioning. Where the model will be implemented will determine the timeliness and complexity for when the models can be put into practice. Models can be developed in an in-house system, a third-party processor, a credit reporting agency, etc. Accurate documentation outlining the specifications of the model will be critical for successful implementation and model audits. Scorecard monitoring will need to be put into place once the model is developed, implemented and put into use. Scorecard monitoring evaluates population stability, scorecard performance, and decision management to ensure that the model is performing as expected over the course of time. If at any time there are variations based on initial expectations, then scorecard monitoring allows for immediate modifications to strategies. With all the right ingredients, the right approach, and the checks and balances in place, your model development process has the potential to come out “just right!”  

By: Tracy Bremmer Preheat the oven to 350 degrees. Grease the bottom of your pan. Mix all of your ingredients until combined. Pour mixture into pan and bake for 35 minutes. Cool before serving. Model development, whether it is a custom or generic model, is much like baking. You need to conduct your preparatory stages (project design), collect all of your ingredients (data), mix appropriately (analysis), bake (development), prepare for consumption (implementation and documentation) and enjoy (monitor)! This blog will cover the first three steps in creating your model! Project design involves meetings with the business users and model developers to thoroughly investigate what kind of scoring system is needed for enhanced decision strategies. Is it a credit risk score, bankruptcy score, response score, etc.? Will the model be used for front-end acquisition, account management, collections or fraud? Data collection and preparation evaluates what data sources are available and how best to incorporate these data elements within the model build process. Dependent variables (what you are trying to predict) and the type of independent variables (predictive attributes) to incorporate must be defined. Attribute standardization (leveling) and attribute auditing occur at this point. The final step before a model can be built is to define your sample selection. Segmentation analysis provides the analytical basis to determine the optimal population splits for a suite of models to maximize the predictive power of the overall scoring system. Segmentation helps determine the degree to which multiple scores built on an individual population can provide lift over building just one single score. Join us for our next blog where we will cover the next three stages of model development:  scorecard development; implementation/documentation; and scorecard monitoring.