Probing Digital Footprints and Reaching for Inherent Preferences: A Cause-Disentanglement Approach to Personalized Recommendations

Cong Wang (), Yansong Shi (), Xunhua Guo () and Guoqing Chen ()
Additional contact information
Cong Wang: Guanghua School of Management, Peking University, Beijing 100871, China
Yansong Shi: School of Management, Fudan University, Shanghai 200433, China; and School of Economics and Management, Tsinghua University, Beijing 100084, China
Xunhua Guo: China Retail Research Center, School of Economics and Management, Tsinghua University, Beijing 100084, China
Guoqing Chen: School of Economics and Management, Tsinghua University, Beijing 100084, China

Information Systems Research, 2025, vol. 36, issue 3, 1314-1332

Abstract: The abundance of multiple types of consumer digital footprints recorded on e-commerce platforms has fueled the design of personalized recommender systems for decision support. However, capturing consumers’ inherent preferences for effective recommendations based on consumer digital footprints can be challenging because of the multitude of factors driving consumer behaviors. Model training and recommendation outcomes may become biased if other factors are inappropriately recognized as consumers’ inherent preferences in the learning process. Drawing on consumer behavior theories, we tease out various factors that drive consumers’ digital footprints at different consumption stages. We develop a novel recommendation approach, namely, DISC (Disentangling consumers’ Inherent preferences, item Salience effect, and Conformity effect), which leverages disentangled representation learning with a causal graph to derive the effect of each factor driving consumer behaviors. This approach provides personalized and interpretable recommendations based on the inference of consumers’ normative inherent preferences. The DISC model’s identifiability is demonstrated through theoretical analysis, enabling rigorous causal inference based on observational data. To evaluate DISC’s performance, extensive experiments are conducted on real-world data sets with a carefully designed protocol. The results reveal that DISC outperforms state-of-the-art baselines significantly and possesses good interpretability. Moreover, we illustrate the potential impact of different marketing strategies’ by intervening on the disentangled causes through follow-up counterfactual analyses based on the causal graph. Our study contributes to the literature and practice by causally unpacking the behavioral mechanism behind consumers’ digital footprints and designing an interpretable personalized recommendation approach anchored in their inherent preferences.

Keywords: recommender system; multiple digital footprints; inherent preferences; causal graph; disentangled representation learning; interpretability (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/isre.2023.0181 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:orisre:v:36:y:2025:i:3:p:1314-1332

Access Statistics for this article

More articles in Information Systems Research from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().