Store Sales - Time Series Forecasting

Use machine learning to predict grocery sales

Welcome to the Store Sales - Time Series Forecasting Challenge!

Kaggle’s Time Series Forecasting challenge focuses on utilizing time-series forecasting to predict store sales for Corporación Favorita, a major grocery retailer based in Ecuador.

The challenge involves building a model that can accurately predict unit sales for thousands of items sold at various Favorita stores. The training dataset comprises dates, store and item information, promotions, and unit sales, providing a chance to practice and improve your machine learning skills.

Accurate forecasting is critical for grocery stores, as it ensures the right amount of inventory is purchased, avoiding waste and lost revenue. Currently, subjective forecasting methods lack data and cannot be automated. However, machine learning offers a solution that can help retailers predict demand more accurately, especially as they expand to new locations, add new products, and deal with evolving seasonal tastes and unpredictable marketing trends.

By participating in this competition, you can contribute to improving forecasting accuracy and helping retailers provide customers with the right products at the right time.


  • Start Date: October 6, 2021
  • End Date: This competition does not have an end date.

Sponsored by Saturn Cloud

The dataset is hosted by Saturn Cloud, which will be available for download. Each participant can use the Saturn Cloud computing environment, which provides 100 free hours of compute per participant, and a Python environment. Message Saturn Cloud support and say, "I'm competing in the Store Sales - Time Series Forecasting challenge." You'll be upgraded from the standard free tier to 100 hours of compute! Click the link below to get started with the competition.