{"ID":2885693,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04269","arxiv_id":"2508.04269","title":"A Visual Tool for Interactive Model Explanation using Sensitivity Analysis","abstract":"We present SAInT, a Python-based tool for visually exploring and understanding the behavior of Machine Learning (ML) models through integrated local and global sensitivity analysis. Our system supports Human-in-the-Loop (HITL) workflows by enabling users - both AI researchers and domain experts - to configure, train, evaluate, and explain models through an interactive graphical interface without programming. The tool automates model training and selection, provides global feature attribution using variance-based sensitivity analysis, and offers per-instance explanation via LIME and SHAP. We demonstrate the system on a classification task predicting survival on the Titanic dataset and show how sensitivity information can guide feature selection and data refinement.","short_abstract":"We present SAInT, a Python-based tool for visually exploring and understanding the behavior of Machine Learning (ML) models through integrated local and global sensitivity analysis. Our system supports Human-in-the-Loop (HITL) workflows by enabling users - both AI researchers and domain experts - to configure, train, e...","url_abs":"https://arxiv.org/abs/2508.04269","url_pdf":"https://arxiv.org/pdf/2508.04269v1","authors":"[\"Manuela Schuler\"]","published":"2025-08-06T09:53:31Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}