Representation Learning for Predicting Customer Orders

The ability to predict future customer orders is of significant value to retailers in making many crucial operational decisions. Different from next basket prediction or temporal set prediction, which focuses on predicting a subset of items for a single user, this paper aims for the distributional information of future orders, i.e., the possible subsets of items and their frequencies (probabilities), which is required for decisions such as assortment selection for front-end warehouses and capacity evaluation for fulfillment centers. Based on key statistics of a real order dataset from Tmall supermarket, we show the challenges of order prediction. Motivated by our analysis that biased models of order distribution can still help improve the quality of order prediction, we design a generative model to capture the order distribution for customer order prediction. Our model utilizes representation learning to embed items into a Euclidean space and design a highly efficient SGD algorithm to learn the item embeddings. Future order prediction is done by calibrating orders obtained by random walks over the embedding graph. The experiments show that our model outperforms all the existing methods. The benefit of our model is also illustrated with an application to assortment selection for front-end warehouses.

Automated summary

The paper discusses the importance of predicting future customer orders for retailers and introduces a generative model to capture order distribution, utilizing representation learning and SGD algorithm to optimize prediction performance.