Predicting Bankruptcies: Do You Know What You Don’t Know?
This question sounds absurd. But this is one of the most important questions lenders must ask themselves when making consumer credit decisions. Sure, credit scores provide information about a consumer’s potential creditworthiness. Such scores help you make a better informed decision, but they leave blind spots. One of these blind spots is consumer bankruptcy. A traditional credit score on its own may not be a good indicator of a consumer’s bankruptcy risk. So ask yourself, do you have a 360-degree view of a customer’s credit risk? And if not, do you know what’s missing?
Knowing Your Blind Spots
Though bankruptcy filings are on a decline, consumer debt has risen to almost $4 trillion in 2018. This is a 7.6% increase from 2017.
One sector of the population, in particular, is at risk for bankruptcy. According to the Wall Street Journal, “the rate at which Americans age 65 and older are filing for bankruptcy has more than tripled since 1991 amid reductions in the social safety net and a shift away from pensions.” At the same time, financial institutions lose billions to consumer bankruptcy filings to the tune of almost 50 percent of total losses.
Compounding the challenge is the fact that many bankruptcies come as a surprise to lenders. This is because many are filed by consumers that exhibit good credit behaviors. Identifying potentially profitable, creditworthy customers from bankruptcies requires monitoring, accuracy and robust predictive analytics.
Keeping an Eye on Consumer Bankruptcy Risk
Predicting bankruptcies also requires persistent and constant monitoring of consumers’ credit portfolios. Why is it important for lenders to protect themselves at every phase of the customer engagement process? It will help avoid losses and allow you to focus only on creditworthy individuals.
Integrating bankruptcy monitoring at various stages of the customer life cycle is simple. From pre-screening and up-selling to deepening customer engagement and loyalty, you may check bankruptcy scores online or offline. Your retention and customer management efforts will be more precise and yield better results when you’re connecting with your best customers. Further, you can easily identify those who may be at risk or already in collections and avoid them, which can help preserve budget and resources. Understanding bankruptcy risk also adds an extra layer of protection when preparing for an economic downturn, evaluating potential customers for a subprime credit offer or even when launching a new product in an under-served market.
Predicting Bankruptcies Requires New Data Science
Currently, most credit scoring algorithms use logistical regression to compute scores. This technique is limited to 30-50 variables and doesn’t have the capability to learn new things on its own. Large volumes of data combined with new technologies provides the ability to gain deeper, more accurate insights. Advanced modeling techniques like machine learning and neural networks provide deeper insights into data.
Incorporating trended data into risk decisioning can help you more actively monitor your portfolio. Understanding the trajectory of credit behavior, you can readily identify customers who may file for bankruptcy. Trended data can also help you determine future bankruptcy potential, helping you avoid further loss through early detection.
Protect Against Bankruptcy Losses with Stronger Predictive Scoring
Knowing what you don’t know just got easier with tools like Bankruptcy Navigator Index. Bankruptcy Navigator Index (BNI) is an FCRA scoring model that predicts the likelihood that an individual will file for bankruptcy within the following 24 months. BNI uses advanced data science such as the patented NeuroDecision Technology for greater predictive accuracy. BNI combines consumer credit data with proven analytics to help you recognize and mitigate bankruptcy risk.
Learn more about how we’re helping lenders leverage the power of data and advanced data science to predict bankruptcies.
Recommended For You
The Numbers Spark More Questions I’m Prasanna Dhoré, Chief Data & Analytics Officer at Equifax. Like you, I’ve been spending […]
Many auto lenders and dealerships are aware of the general risks associated with fraud. However, synthetic identity fraud is especially […]
Ground-breaking modeling techniques fueled by machine learning and explainable artificial intelligence (xAI) are transforming the credit decisioning landscape. They are […]
In this blog series, Equifax and expert guest speakers answer top of mind questions from attendees on the weekly Market […]