Proxies During a Pandemic: Using Data Analytics to “See Around Corners”
In the midst of the COVID pandemic turmoil, retailer CVS knew they couldn’t rely on historical data for future planning. So they turned to WorldQuant Predictive (WQP) and their multi-disciplinary Global Research Network. Using AI and ML tools on WQP’s proprietary platform, the WQP/CVS team looked at +50 disparate, open-source, alternative datasets. Through an iterative process they quickly generated a customized predictive model for CVS’s business.
One of the surprising sources for predictive datasets was Zillow. Not previously associated with modeling, it turned out to be the best proxy and uncovered a hidden alpha signal that helped CVS predict future consumer behavior. This proxy data predicted store sales to within ±2% accuracy. Zillow data was also used to create early warning indicators.
The takeaways can be extended to many common prediction problems crucial to retailers. In this webinar, you’ll learn how your organization can use this approach for a competitive edge during COVID and beyond.
Moderated by Alex Woodie:
Alex Woodie is the Managing Editor of Datanami, which covers data-intensive computing in research and enterprise and provides expert commentary on an ongoing basis around analytics and software for managing “big data” problems. Alex brings extensive experience from the IBM midrange marketplace, including topics such as servers, ERP applications, programming, databases, security, high availability, storage, business intelligence, cloud, and mobile enablement.