Decathlon Achieves 11-15 Point Forecast Accuracy Improvement Using Chronos-2 on AWS

Sporting goods retailer Decathlon deployed AWS's Chronos-2 model to forecast demand for tens of thousands of products, improving accuracy significantly.

According to Amazon AWS, Decathlon, one of the world’s largest sporting goods retailers, has successfully deployed the Chronos-2 forecasting model on AWS to improve its demand forecasting operations. The retailer uses the system to forecast weekly demand for tens of thousands of products across multiple continents.

The implementation resulted in forecast accuracy improvements of 11-15 points while simultaneously reducing operational complexity, according to the AWS announcement. Decathlon runs weekly inference using the Chronos-2 model to maintain its demand forecasting at scale. The deployment demonstrates how large retailers are leveraging AWS’s AI tools to optimize supply chain operations across their global networks.