Analytics Could Help Predict Store Closings
AI and other technology could help analyze data to help determine future of stores.
Using Artificial intelligence (AI) and other technology to analyze data around stores could help investors and other stakeholders determine the future of those locations and help predict store closings and other factors. This is according to a report from System2, a company that uses AI and other technologies for big data analysis.
System2 has assessed that as many as 197 J.C. Penney stores could be at risk of closing, on top of the 140 the retailer has already closed. The analysis was first reported by Bloomberg Technology. According to System2, those stores have more than a 64 percent chance of closing. The firm reached that figure by applying machine learning to collected data around J.C. Penney's stores to determine those most at risk. The collected data included foot traffic, the income of people who live nearby, as well as their home prices, and many other variables.
According to Bloomberg, System2 founder Matei Zantreanu says that AI and machine learning can provide better predictors of the future of a particular store than conventional information usually used by investors to make their decisions.
“There’s new data out there,” Zantreanu explained. “But then what we try to focus on is how do we use this data in a smarter way?
System2 uses aggregated location pings from mobile phones to create a dynamic picture of store traffic and where shoppers come from. Then they can use average household incomes and home prices to create profiles of customers for a specific store. System2 specifically used this kind of information to determine what it was about dead stores that doomed them to fail.
System2 is not the only company using data to predict possible store closings; inMarket is using mobile location data to predict retail store closures, as Marketingland reported. The company’s SDK (software development kit) has been integrated into 700 apps, covering some 50 million active mobile devices in the U.S. this provides a slew of data that uses the frequency of retail store visits to create loyalty metrics and retail benchmarks to help predict the future solidity of a particular location.
As the retail landscape continues to adjust to the new reality of today’s shoppers and their behaviors, such predictive analysis can serve as a valuable tool for companies as they make decisions about the future of their locations.