【会议】Using Transactions Data to Improve Consumer Returns Forecasting
发布者：沙晓燕 发布时间：2021-09-10 浏览次数：22
Time: 10:00 AM-11:00 AM, Sept. 11, 2021
Voov Meeting: 943 284 094
Speaker: Prof. Guangzhi Shang
Dr. Guangzhi Shang is the Jim Moran Associate Professor of Business Administration in the Department of Business Analytics, Information Systems and Supply Chain at Florida State University’s College of Business. His current research interests include consumer returns management, service labor issues, blockchain technology, crowdsourcing platforms, and new revenue management technologies. His research has been published in leading academic journals such as Production and Operations Management, Journal of Operations Management and Decision Sciences. Dr. Shang is a department editor for the Journal of Operations Management (Empirical Research Methods Department) and Decision Sciences (Retail Operations Department). His review contribution to the academic community was recognized with a 2018 Best Reviewer Award from the Journal of Operations Management, a nomination of the 2017 Rest Reviewer Award of Production and Operations Management and the 2019 Outstanding Reviewer Award of Decision Sciences.
Abstract: Although generous return policies have been shown to have marketing benefits, such as a higher willingness to pay and a higher purchase frequency, counterbalancing these benefits is an increased volume of consumer returns, which presents significant operational challenges for both retailers and original equipment manufacturers (OEMs). Since accurate return forecasts are inputs into strategic and tactic decision support tools for operations managers, advancements in better forecast accuracy can yield significant savings from the returns management practice. We propose a forecasting approach that incorporates transaction-level data, such as purchase and return timestamps, and predicts future return quantities using a two-step “predict-aggregate” process. To enhance the generalizability of our framework, we test it on two distinct datasets provided by a bricks-and-mortar electronics retailer and an online jewelry retailer. We find that our approach demonstrates significant forecasting error reduction, in the range of 10–20%, over benchmark models constructed from common industry practices and the existing literature. As our approach leverages the same data inputs as existing models, it can be easily adapted by practitioners. We also consider a number of extensions to generalize our approach into contexts such as restricted return time windows, new product returns, and inflated same-day returns. Last, we discuss broad implications of return forecast accuracy improvements in the areas such as inventory management, staffing level, reverse logistics, and return recovery decisions.