Demands Satiated or Not? A Psychology-Informed Deep Probabilistic Approach to Offline Store Recommendations

Offline store recommendations have emerged as a powerful tool in the mall industry for enhancing the customer experience and boosting mall revenue. Existing research focuses on mining behavioral patterns but largely overlooks the underlying psychological mechanisms that drive store choice behaviors. To bridge this gap, our study is a pioneering work that incorporates demand satiation to enhance offline store recommendations. Informed by optimum stimulation level (OSL) theory, we propose a novel dynamic demand satiation model (DDSM) featuring two adaptive components: (1) the satiation decay component takes an exponential form to capture the decay of satiation over time, and (2) the intention adaptation component utilizes deep recurrent neural networks to account for diverse shopping intentions. Using a real-world offline shopping data set, we empirically demonstrate and analyze the superior performance of our method over several classic and state-of-the-art methods. Additionally, we conduct an interpretability analysis to gain insights into the model’s recommendation mechanism. We also explore the role of demand satiation in enhancing the offline shopping experience through a user study.

History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning.

Funding: J. He, W. Wu, and J. Guo are supported by the National Natural Science Foundation of China [Grants 72001128, 72101139, and 72394360]. X. Fang is not supported by any funds and is not associated with any of the above mentioned funds.

Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0403) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2023.0403). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/.