Data Study Group Final Report: CatsAi

Communicating high-street bakery sales predictions using counterfactual explanations


This challenge aims to help CatsAi better serve their client (a large wholesaler) to estimate bakery orders to reduce waste and under delivery. The main tasks were to predict high-street sales based on meteorological factors and apply explainability techniques to effectively communicate their outputs to the client.

During the challenge, we explored data relating to sales for a key client operating in a single country. The data comprised four different sections: location, products, weather and product sales, our target variables. Each group of variables provided several details about particular weather conditions or location (maximum temperature, visibility, competitor index, etc.), providing fine-grained information about sales.

Citation information

Data Study Group team. (2021, October 11). Data Study Group Final Report: CatsAi. Zenodo.

Turing affiliated authors