Data-driven demand forecast for O2O operations: an adaptive hierarchical incremental approach

• Main Authors: Dai, Hongyan, Xiao, Qin, Chen, Songlin, Zhou, Weihua
• Other Authors: School of Mechanical and Aerospace Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Mechanical engineering; Social sciences::Economic theory; Forecasting; Data-Driven
• Online Access: https://hdl.handle.net/10356/172868
• Institution: Nanyang Technological University

Online-to-offline (O2O) refers to a new type of e-commerce that combines online order acquisition and offline on-demand order fulfillment service. The daily demand for O2O stores is affected by both online and offline factors. Given the highly dynamic online operation and offline environment, the effects of latent factors may change over time. Therefore, forecasting at the aggregation level may be subject to real-time information loss and structural changes and may generate less accurate forecasts. In this study, we propose an adaptive hierarchical incremental forecasting (AHIF) approach to forecast daily O2O store demand, which integrates an incremental method to handle structural changes and a hierarchical process to capture valuable real-time information. A data-driven O2O demand forecast application based on the AHIF approach was implemented in one of the largest O2O platforms in China in an actual business environment. The proposed AHIF approach can significantly improve forecasting accuracy compared with conventional forecasting methods, as shown by the results of the numerical analysis. By tracing and quantifying the contribution of performance improvement by the proposed algorithm, this study provides valuable insights for future algorithm development and operational improvement concerning O2O operations management.