Making the Newsvendor Smart – Order Quantity Optimization with ANNs for a Bakery Chain

Accurate demand forecasting is particularly crucial for products with short shelf life like bakery products. Over- and underestimation of customer demand affects not only profit margins of bakeries but is also responsible for 600,000 metric tons of food waste every year in Germany. To solve this problem, we develop an IT artifact based on artificial neural networks, which is automating the manual order process and capable of reducing costs as well as food waste. To test and evaluate our artifact, we cooperated with an SME bakery chain from Germany. The bakery chain runs 40 points of sale (POS) in southern Germany. After algorithm based reconstructing and cleaning of the censored sales data, we compare two different data-driven newsvendor approaches for this inventory problem. We show that both models are able to significantly improve the forecast quality (cost savings up to 30%) compared to human planners