How Crowdsourced Data Helps to Predict Credit Risk

Learn how adding crowdsourced data to the Frisk® score model helps you to do a better job of predicting business bankruptcy.

Is crowdsourced behavior from your credit peers a good predictor of bankruptcy risk?

Next week at the CRF Forum and Expo in Chicago, Camilo Gomez, PhD and SVP, Quantitative Analytics at CreditRiskMonitor, will share new research that answers this very question.

Turns out, a unique pattern of behavioral data derived from a very specific group of credit professionals does in fact predict bankruptcy, and helps our proprietary FRISK® score financial risk model target credit risks sooner. So in June, we added crowdsourced online behavior to the FRISK® score model. 

Want to learn more? If you'll be at the CRF Forum and EXPO in Chicago next month, come to the CreditRiskMonitor User Group. You’ll learn: 

  • How this online data pattern helps us to identify high-risk companies, sooner

  • Why it takes multiple sources of data -- financial statements, agency debt ratings, stock market behavior, and now, subscriber behavior -- to predict financial risk

  • How the enhanced FRISK® score model can help you target portfolio risks, and benefit your risk management process. 

For a sneak preview, here are several excerpts from a recent webinar with Dr. Gomez on this topic.


Top Questions About the Enhanced FRISK® Score, Answered: Q & A with Dr. Gomez

Q: Why did you add subscriber behavior to the FRISK® score model?

Dr. Gomez: The FRISK® score has always predicted public company financial distress. But we recently found that the aggregate pattern of activity on our website is another powerful indicator of public company financial health.

We discovered that when credit executives use our service to examine a company they’re concerned about, the pattern of clicks and pages looked at is correlated with the likelihood of extreme financial distress, and ultimately, bankruptcy, for the companies in our database. 

This credit manager behavior, aggregated across a large number of subscribers, complements the other factors in our model (financial statement data, stock market sentiment, agency ratings, etc.), for an even more accurate financial risk score.   

Q: Increasing model accuracy from 95% to 96% doesn’t seem like a big change. Why is this news significant? 

Dr. Gomez: On the surface, the difference in accuracy may seem small, but there's actually a big difference in the timeliness of the financial risk prediction we now make. You can see this on the two graphs below, which show the probability of bankruptcy associated with each point on the FRISK® score scale, before and after the enhancement.

The graph on the left shows the FRISK® without this behavioral factor, while the graph on the right includes it. 

Looking at the graph on the right, the FRISK® score “1” bar is now over 50%, where before it was only 35%. The shift in distribution across the entire scale, moving more companies into the “red zone” and identifying higher risk companies sooner, shows the impact of the change.

These graphs show the effectiveness of the FRISK® score at identifying financially distressed companies that filed for bankruptcy, at each point along the FRISK® score scale (the “capture fraction”), before and after crowdsourced data
These graphs show the effectiveness of the FRISK® score at identifying financially distressed companies that filed for bankruptcy, at each point along the FRISK® score scale (the “capture fraction”), before and after crowdsourced data.

Q: How does this enhancement help the typical CreditRiskMonitor subscriber?

Dr. Gomez: A more accurate bankruptcy model enables our subscribers to detect big financial risks sooner, mitigate these portfolio risks in a more timely way, and avoid loss. 
 

Still have questions about how the enhanced FRISK® score predicts public company bankruptcy risk? 

Want to know more, but not attending the CRF Forum and Expo in Chicago next month? Watch the webinar replay, with Dr. Gomez

If you're attending the CRF conference, we hope you'll join our user group and workshop on Monday 8/8, to learn more about this exciting topic. Hope to see you there!

Register Now: Attend the CreditRiskMonitor User Group at the CRF Forum and EXPO

About CreditRiskMonitor

CreditRiskMonitor is a financial news and analysis service designed to help professionals stay ahead of public company risk quickly, accurately and cost-effectively. More than 35% of the Fortune 1000, plus thousands more worldwide, rely on our commercial credit reporting and predictive risk analytics for assessing the financial stability of over 58,000 global public companies.

At the core of CreditRiskMonitor’s service is its 96% accurate FRISK® score, which is formulated to predict public company bankruptcy risk. One of four key components calculated in the FRISK® score is crowdsourced subscriber activity. This unique system tracks subscribers' patterns of research activity, capturing and aggregating the real-time concerns of what are essentially the key gatekeepers of corporate credit. Other features of CreditRiskMonitor’s service include timely news alerts, the Altman Z” score, agency ratings, financial ratios and trends. CreditRiskMonitor’s network of trade contributors provides more than $135 billion in trade data on their counterparties every month, giving them visibility into their biggest dollar risks.