Guiding Public Health Policy by Using Grocery Transaction Data to Predict Demand for Unhealthy Beverages

Abstract

Sugar-Sweetened Beverages (SSB) are the primary source of artificially added sugar and cause many chronic diseases. Taxation of SSB has been proposed, but limited evidence exists to guide this public health policy. Grocery transaction data, with price, discounting and other product attributes, present an opportunity to evaluate the likely effects of taxation policy. Sales are non-linearly associated with price and are affected by the prices of multiple competing brands. We evaluated the predictive performance of Boosted Decision Tree Regression (B-DTR) and Deep Neural Networks (DNN) that account for the non-linearity and competition, and compared their performance to a benchmark regression, the Least Absolute Shrinkage and Selection Operator (LASSO). B-DTR and DNN showed a lower Mean Squared Error (MSE) of prediction in the sales of major SSB brands in comparison to LASSO, indicating a superior accuracy in predicting the effectiveness of SSB taxation. We have demonstrated how machine learning methods applied to large transactional data from grocery stores can provide evidence to guide public health policy.