Demystifying Sequential Recommendations: Counterfactual Explanations via Genetic Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Scarcelli, Domiziano, Betello, Filippo, Perelli, Giuseppe, Silvestri, Fabrizio, Tolomei, Gabriele
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912521607184384
author Scarcelli, Domiziano
Betello, Filippo
Perelli, Giuseppe
Silvestri, Fabrizio
Tolomei, Gabriele
author_facet Scarcelli, Domiziano
Betello, Filippo
Perelli, Giuseppe
Silvestri, Fabrizio
Tolomei, Gabriele
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03606
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Demystifying Sequential Recommendations: Counterfactual Explanations via Genetic Algorithms
Scarcelli, Domiziano
Betello, Filippo
Perelli, Giuseppe
Silvestri, Fabrizio
Tolomei, Gabriele
Information Retrieval
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.
title Demystifying Sequential Recommendations: Counterfactual Explanations via Genetic Algorithms
topic Information Retrieval
url https://arxiv.org/abs/2508.03606