Machine Learning Seminar

Sales Forecasting Accuracy: A tensor factorization approach with demand awareness

by

Xuan Bi
Information & Decision Sciences
Carlson School of Management
University of Minnesota

Wednesday, September 23, 2020
3:30–4:30 pm

View recording here

Due to accessible big data collections from consumers, products, and stores, advanced sales forecasting capabilities have drawn great attention from many companies especially in the retail business because of its importance in decision making. Improvement of the forecasting accuracy, even by a small percentage, may have a substantial impact on companies' production and financial planning, marketing strategies, inventory controls, supply chain management, and eventually stock prices. Specifically, our research goal is to forecast the sales of each product in each store in the near future. Motivated by tensor factorization methodologies for personalized context-aware recommender systems, we propose iv{a novel approach} called the Advanced Temporal Latent-factor Approach to Sales forecasting (ATLAS), which achieves accurate and individualized prediction for sales by building a single tensor-factorization model across multiple stores and products. Our contribution is a combination of: tensor framework (to leverage information across stores and products), a new regularization function (to incorporate demand dynamics), and extrapolation of tensor into future time periods using state-of-the-art statistical (seasonal auto-regressive integrated moving-average models) and machine-learning (recurrent neural networks) models. The advantages of ATLAS are demonstrated on iv{eight datasets} collected by the Information Resource, Inc., where a total of 165 million weekly sales transactions from more than 1,500 grocery stores over 15,560 products are analyzed.


Xuan Bi is an Assistant Professor of Information and Decision Sciences at the Carlson School of Management. He holds a PhD in Statistics from the University of Illinois at Urbana-Champaign and was a postdoc at Yale University before joining the University of Minnesota. Dr. Bi’s research mainly revolves around machine learning methodologies for personalization, such as recommender systems, and has several articles published on top journals in Statistics. Dr. Bi also holds broad interests in other machine learning and data science areas, such as differential privacy, product forecasting, and imaging data analysis, and is open to opportunities for collaboration.