Demystifying Sequential Recommendations: Counterfactual Explanations via Genetic Algorithms
By: Domiziano Scarcelli , Filippo Betello , Giuseppe Perelli and more
Potential Business Impact:
Shows why a website suggests certain things.
Sequential Recommender Systems (SRSs) have demonstrated remarkable effectiveness in capturing users' evolving preferences. However, their inherent complexity as "black box" models poses significant challenges for explainability. This work presents the first counterfactual explanation technique specifically developed for SRSs, introducing a novel approach in this space, addressing the key question: What minimal changes in a user's interaction history would lead to different recommendations? To achieve this, we introduce a specialized genetic algorithm tailored for discrete sequences and show that generating counterfactual explanations for sequential data is an NP-Complete problem. We evaluate these approaches across four experimental settings, varying between targeted-untargeted and categorized-uncategorized scenarios, to comprehensively assess their capability in generating meaningful explanations. Using three different datasets and three models, we are able to demonstrate that our methods successfully generate interpretable counterfactual explanation while maintaining model fidelity close to one. Our findings contribute to the growing field of Explainable AI by providing a framework for understanding sequential recommendation decisions through the lens of "what-if" scenarios, ultimately enhancing user trust and system transparency.
Similar Papers
A Reinforcement Learning Method to Factual and Counterfactual Explanations for Session-based Recommendation
Social and Information Networks
Explains why you see certain online suggestions.
Comparative Explanations via Counterfactual Reasoning in Recommendations
Information Retrieval
Shows why you like something by comparing it.
Counterfactual Language Reasoning for Explainable Recommendation Systems
Artificial Intelligence
Shows why a computer suggests things you might like.