Decathlon Boosts Demand Forecasting with Chronos-2 on AWS

Vianney Bruned· August 28, 2026 View original

Key takeaways

  • Chronos-2 on AWS improved Decathlon's demand forecasting accuracy by 11-15 points.
  • The solution significantly reduced operational complexity and inference costs.
  • CPU-only instances were sufficient for cost-effective weekly inference.
  • Scalable AI/ML tools can optimize critical retail operations.

Who benefits

RetailSupply ChainLogisticsManufacturing

Summary

Decathlon, a major sporting goods retailer, significantly improved its weekly demand forecasting accuracy by 11-15 points by deploying Chronos-2 on AWS. This implementation also reduced operational complexity and achieved very low inference costs on CPU-only instances.

Decathlon, a global leader in sporting goods retail, has successfully scaled its demand forecasting operations using Chronos-2 deployed on Amazon Web Services. The company manages weekly demand predictions for a vast inventory of products across numerous international markets. By adopting this solution, Decathlon achieved a notable improvement in forecast accuracy, ranging from 11 to 15 percentage points. Furthermore, the implementation led to a reduction in operational overhead and demonstrated remarkable cost efficiency, with weekly inference runs costing approximately $0.03 on standard CPU instances.

Why it matters

This case study demonstrates how advanced AI/ML tools can deliver significant business value through improved accuracy and cost efficiency in critical operations like supply chain and inventory management.

How to implement this in your domain

  1. 1Evaluate existing demand forecasting models for potential accuracy and cost improvements.
  2. 2Research Chronos-2 and similar open-source time series forecasting libraries for applicability.
  3. 3Pilot a Chronos-2 deployment on a cloud platform like AWS, starting with a subset of products.
  4. 4Measure the impact on forecast accuracy and operational costs against current benchmarks.
  5. 5Scale the solution across the entire product catalog if the pilot proves successful.

Original post by Vianney Bruned

"Decathlon, one of the world's largest sporting goods retailers, forecasts weekly demand for tens of thousands of products across multiple continents. Learn how they deployed Chronos-2 on AWS to improve forecast accuracy by 11-15 points while cutting operational complexity and run…"

View on X

Originally posted by Vianney Bruned on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses