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

Jiangning He, Weikun Wu, Jiayi Guo, Xiao Fang

Abstract: 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.