Paper accepted at ECML PKDD 2026!
🎉 We’re thrilled to announce that our paper has been accepted at ECML PKDD (the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases)!
This paper presents X-Insight, a Streamlit-based platform for explainable unsupervised analysis of tabular data. The platform integrates data exploration, preprocessing, multiple clustering algorithms, global and local explainability, and counterfactual analysis within a single end-to-end workflow, with optional LLM-assisted interpretation that summarizes and contextualizes the outputs of the XAI modules. While general-purpose and applicable to any tabular dataset, it is demonstrated on a systemic sclerosis cohort for subgroup discovery. X-Insight promotes trustworthiness and interpretability through interactive visualizations, fidelity-assessed surrogate rules, fairness checks, and clinically constrained counterfactuals, providing actionable insights for researchers and clinicians.
