Machine Learning Times
Machine Learning Times

4 weeks ago
Wise Practitioner – Predictive Analytics Interview Series: William WIlkins & Carrie Lu Ph.D. at Safety National Casualty Corporation


By: Eric Siegel, Program Co-Chair, Predictive Analytics World for Financial

In anticipation of their upcoming conference presentation at Predictive Analytics World for Financial Las Vegas, May 31-June 4, 2020, we asked William WIlkins, Chief Risk and Data Analytics Officer and Carrie Lu Ph.D., Senior Data Scientist at Safety National Casualty Corporation, a few questions about their deployment of predictive analytics. Catch a glimpse of their presentation, The Conundrum of Individuality on Longer Term Predictions, and see what’s in store at the PAW Financial conference in Las Vegas.

Q: In your work with predictive analytics, what behavior or outcome do your models predict?

A: For Safety National a typical claim is reported 5 to 10 years after the date of injury.  With predictive analytics,  Safety National can address these claims as soon as 12 months after the date of injury.

Q: How does predictive analytics deliver value at your organization – what is one specific way in which it actively drives decisions or operations?

A: With Safety National’s expertise in handling high value claims, the sooner Safety can get involved, the better the outcome for both the injured worker and our insured clients.   Safety National has multiple programs and claims actions that can help workers get the care that is necessary and expedite recovery.

Q: Can you describe a quantitative result, such as the predictive lift of your model or the ROI of an analytics initiative?

A: The quantification aspect will never be fully known and for Safety National it is not all about ROI or dollars & cents.  Early intervention changes the course of many things, not just the cost of the claim.  More appropriate and early care, benefits the injured worker; who can then lead a more full and productive life.  That in turn shows the employees of the insured, that they matter and helps build a good company culture.

Q: What surprising discovery or insight have you unearthed in your data?

A: That real time data is not all that much more important than monthly snap shots on complicated high transaction claims.  Complex claims are just that, complex.  Daily modeled transactions can shift perspective too quickly and miss the totality of situation for the long run.

Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.

A: Predictive models can be built to predict the potential cost of a workers’ comp. But, given the individualistic nature of each claim and the potential financial ramifications, finding the right balance in identification and action is not just a numbers game.  The individuality matters greatly.


Don’t miss their presentation, The Conundrum of Individuality on Longer Term Predictions, at PAW Financial on Tuesday, June 2, 2020 from 11:20 to 11:40 AM. Click here to register for attendance.

By: Eric Siegel, Program Co-Chair, Predictive Analytics World for Financial

Leave a Reply

Pin It on Pinterest

Share This