AWS Startups Blog

Roofstreet: Using AI to Predict Travel Lines

Unexpected issues can impact travel plans. Roofstreet, an AI built to predict travel routes, informs users of incidents along their travel lines ahead of time. Paired with transport applications and utilizing smartphone geolocation data, Roofstreet detects and predicts the travel route an individual may take within one to three hours. Due to the statistics gleaned from this information, Roofstreet calculates the volume of people passing by a specific point and their intended destination. Retailers can use this information to plan where and when to open their shops, and to predict how much traffic they can expect. Roofstreet’s AI acts as an SDK (software development kit) with built-in functions and placed inside a number of mobile applications. Obtaining 200-300 geolocation points per person each day, Roofstreet’s AI can rebuild and recognize past trips and recurring routes, and uses this to predict an individual’s next trip.

Jean-Baptiste Delattre, co-founder of Roofstreet, states that Roofstreet’s customers are GDPR compliant and that mechanisms are in place to ensure personal data is processed carefully. Roofstreet’s AI uses GPS to obtain location data, which Delattre believes is the most accurate source of location information available today.

Michelle Kung

Michelle Kung

Michelle Kung currently works in startup content at AWS and was previously the head of content at Index Ventures. Prior to joining the corporate world, Michelle was a reporter and editor at The Wall Street Journal, the founding Business Editor at the Huffington Post, a correspondent for The Boston Globe, a columnist for Publisher’s Weekly and a writer at Entertainment Weekly.