The document discusses a project that uses machine learning algorithms to predict sales on Black Friday using customer data from previous years. It analyzes a dataset containing customer attributes and purchase amounts. Three regression models - Lasso, linear, and random forest regression - are trained on 80% of the data and tested on the remaining 20%. The random forest model achieved the highest prediction accuracy according to the root mean square error metric. Retailers can use these predictions to better understand customer purchasing behavior and inform marketing strategies for Black Friday.