M5 Forecasting Competition

M5 Forecasting Competition

Earn PRIZE MONEY and test your skills participating in the M5 Competition - starting March 5, 2020 and finishing June 30, 2020. Register here

The goal of the M5 Competition is to identify the most appropriate method(s) for different types of situations requiring predictions and making uncertainty estimates. Its ultimate purpose is to advance the theory of forecasting and improve its utilization. In addition, a goal is to compare the accuracy/uncertainty of machine learning and deep learning methods vis-à-vis those of standard statistical ones, and assess possible improvements versus the extra complexity and higher costs of using the various methods.

See distribution of prize money here.

Download M5 Competition Guidelines here.

M5 Competition Basics

(1) Uses hierarchical sales data, generously made available by Walmart, starting at the item level and aggregating to that of departments, product categories, stores, and three geographical areas: the US States of California, Texas, and Wisconsin;

(2) In addition to time series data, it also includes explanatory variables such as price, promotions, day of the week, and special events (e.g. Super Bowl, Valentine’s Day, and Orthodox Easter) affecting sales and used to improve forecasting accuracy;

(3) In addition to point forecasts, the distribution of uncertainty is being assessed by asking participants to provide information on four indicative prediction intervals and the median; and

(4) Majority of the more than 43,000 time series display intermittency (sporadic sales including zeros).

Register for M5 Competition here

Thursday, March 5, 2020 - 8:15am to Tuesday, June 30, 2020 - 3:15pm