Using Location Data to Predict what will be Popular

Jan. 5, 2022

  • Profile Picture of Xue Bai


Predicting what stores and products will be popular can help business owners, customers and city officials efficiently prepare for the future.

While trend forecasting has been around for years, Xue Bai, associate professor of marketing and supply chain management at the Fox School, took a novel approach to predict popularity. Bai developed a model based on location-based information to predict which locations will grow in popularity. She and her team relied on mobile apps like Facebook Places, Foursquare and Meetup that allow mobile users to check in to their location and share it with their friends.

Interestingly, the two parts of Bai’s model – the network of friends (social actors) and the locations (social foci) – are mutually reinforcing. This means that not only do friends influence each other to visit the same places, but their friendships can grow stronger by sharing that common experience.