{"url":"/method/shap","slug":"shap","name":"SHAP","full_name":"Shapley Additive Explanations","full_name_withheld":false,"description_markdown":"**SHAP**, or **SHapley Additive exPlanations**, is a game theoretic approach to explain the output of any machine learning model. It connects optimal credit allocation with local explanations using the classic Shapley values from game theory and their related extensions. Shapley values are approximating using Kernel SHAP, which uses a weighting kernel for the approximation, and DeepSHAP, which uses DeepLift to approximate them.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1705.07874v2","title":"A Unified Approach to Interpreting Model Predictions","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/slundberg/shap","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Interpretability","url":"/methods/category/interpretability","pwc_aliases":[]}],"n_papers_tagged":550,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Correlation vs causation in Alzheimer's disease: an interpretability-driven study","date":"2025-06-11","arxiv_id":"2506.10179","n_code_links":0,"syntology":null},{"paper":null,"title":"Neurosymbolic Artificial Intelligence for Robust Network Intrusion Detection: From Scratch to Transfer Learning","date":"2025-06-04","arxiv_id":"2506.04454","n_code_links":0,"syntology":null},{"paper":null,"title":"A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations","date":"2025-06-03","arxiv_id":"2506.03425","n_code_links":0,"syntology":null},{"paper":null,"title":"Predicting Postoperative Stroke in Elderly SICU Patients: An Interpretable Machine Learning Model Using MIMIC Data","date":"2025-06-02","arxiv_id":"2506.03209","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable-AI powered stock price prediction using time series transformers: A Case Study on BIST100","date":"2025-06-01","arxiv_id":"2506.06345","n_code_links":0,"syntology":null},{"paper":null,"title":"A SHAP-based explainable multi-level stacking ensemble learning method for predicting the length of stay in acute stroke","date":"2025-05-30","arxiv_id":"2505.24101","n_code_links":0,"syntology":null},{"paper":null,"title":"Interpretable phenotyping of Heart Failure patients with Dutch discharge letters","date":"2025-05-30","arxiv_id":"2505.24619","n_code_links":0,"syntology":null},{"paper":"/paper/multi-criteria-rank-based-aggregation-for","title":"Multi-criteria Rank-based Aggregation for Explainable AI","date":"2025-05-30","arxiv_id":"2505.24612","n_code_links":1,"syntology":null},{"paper":"/paper/machine-learning-framework-for-characterizing","title":"Machine Learning Framework for Characterizing Processing-Structure Relationship in Block Copolymer Thin Films","date":"2025-05-29","arxiv_id":"2505.23064","n_code_links":1,"syntology":null},{"paper":null,"title":"Document Valuation in LLM Summaries: A Cluster Shapley Approach","date":"2025-05-28","arxiv_id":"2505.23842","n_code_links":0,"syntology":null},{"paper":null,"title":"Triple Attention Transformer Architecture for Time-Dependent Concrete Creep Prediction","date":"2025-05-28","arxiv_id":"2506.04243","n_code_links":0,"syntology":null},{"paper":"/paper/mlran-a-behavioural-dataset-for-ransomware","title":"MLRan: A Behavioural Dataset for Ransomware Analysis and Detection","date":"2025-05-24","arxiv_id":"2505.18613","n_code_links":1,"syntology":null},{"paper":null,"title":"Reverse-Speech-Finder: A Neural Network Backtracking Architecture for Generating Alzheimer's Disease Speech Samples and Improving Diagnosis Performance","date":"2025-05-23","arxiv_id":"2505.17477","n_code_links":0,"syntology":null},{"paper":null,"title":"Computing Exact Shapley Values in Polynomial Time for Product-Kernel Methods","date":"2025-05-22","arxiv_id":"2505.16516","n_code_links":0,"syntology":null},{"paper":null,"title":"Towards Trustworthy Keylogger detection: A Comprehensive Analysis of Ensemble Techniques and Feature Selections through Explainable AI","date":"2025-05-22","arxiv_id":"2505.16103","n_code_links":0,"syntology":null},{"paper":null,"title":"CSAGC-IDS: A Dual-Module Deep Learning Network Intrusion Detection Model for Complex and Imbalanced Data","date":"2025-05-20","arxiv_id":"2505.14027","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable AI for Securing Healthcare in IoT-Integrated 6G Wireless Networks","date":"2025-05-20","arxiv_id":"2505.14659","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable Prediction of the Mechanical Properties of Composites with CNNs","date":"2025-05-20","arxiv_id":"2505.14745","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-adapt-to-position-bias-in-vision","title":"Learning to Adapt to Position Bias in Vision Transformer Classifiers","date":"2025-05-19","arxiv_id":"2505.13137","n_code_links":1,"syntology":null},{"paper":null,"title":"Machine Learning-Based Prediction of Mortality in Geriatric Traumatic Brain Injury Patients","date":"2025-05-19","arxiv_id":"2505.15850","n_code_links":0,"syntology":null},{"paper":"/paper/bensparx-a-robust-explainable-machine","title":"BenSParX: A Robust Explainable Machine Learning Framework for Parkinson's Disease Detection from Bengali Conversational Speech","date":"2025-05-18","arxiv_id":"2505.12192","n_code_links":1,"syntology":null},{"paper":null,"title":"Modeling Aesthetic Preferences in 3D Shapes: A Large-Scale Paired Comparison Study Across Object Categories","date":"2025-05-18","arxiv_id":"2505.12373","n_code_links":0,"syntology":null},{"paper":"/paper/2505-11189","title":"Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAP","date":"2025-05-16","arxiv_id":"2505.11189","n_code_links":1,"syntology":null},{"paper":null,"title":"Financial Fraud Detection Using Explainable AI and Stacking Ensemble Methods","date":"2025-05-15","arxiv_id":"2505.10050","n_code_links":0,"syntology":null},{"paper":"/paper/shap-based-explanations-are-sensitive-to","title":"SHAP-based Explanations are Sensitive to Feature Representation","date":"2025-05-13","arxiv_id":"2505.08345","n_code_links":1,"syntology":null},{"paper":null,"title":"Understanding molecular ratios in the carbon and oxygen poor outer Milky Way with interpretable machine learning","date":"2025-05-13","arxiv_id":"2505.08410","n_code_links":0,"syntology":null},{"paper":null,"title":"A Computational Approach to Epilepsy Treatment: An AI-optimized Global Natural Product Prescription System","date":"2025-05-10","arxiv_id":"2505.09643","n_code_links":0,"syntology":null},{"paper":null,"title":"Deeply Explainable Artificial Neural Network","date":"2025-05-10","arxiv_id":"2505.06731","n_code_links":0,"syntology":null},{"paper":null,"title":"Interpretable SHAP-bounded Bayesian Optimization for Underwater Acoustic Metamaterial Coating Design","date":"2025-05-10","arxiv_id":"2505.06519","n_code_links":0,"syntology":null},{"paper":null,"title":"Interactive Diabetes Risk Prediction Using Explainable Machine Learning: A Dash-Based Approach with SHAP, LIME, and Comorbidity Insights","date":"2025-05-08","arxiv_id":"2505.05683","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/feature-importance","name":"Feature Importance","papers":88},{"task":"/task/xai","name":"Explainable Artificial Intelligence (XAI)","papers":73},{"task":"/task/explainable-artificial-intelligence","name":"Explainable artificial intelligence","papers":72},{"task":"/task/decision-making","name":"Decision Making","papers":59},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":42},{"task":"/task/feature-selection","name":"feature selection","papers":23},{"task":"/task/interpretable-machine-learning","name":"Interpretable Machine Learning","papers":22},{"task":"/task/regression-1","name":"regression","papers":22},{"task":"/task/management","name":"Management","papers":21},{"task":"/task/prediction","name":"Prediction","papers":20},{"task":"/task/time-series-1","name":"Time Series","papers":19},{"task":null,"name":"counterfactual","papers":18},{"task":"/task/fairness","name":"Fairness","papers":16},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":14},{"task":"/task/classification-1","name":"Classification","papers":14},{"task":"/task/diagnostic","name":"Diagnostic","papers":14},{"task":"/task/benchmarking","name":"Benchmarking","papers":13},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":12},{"task":"/task/binary-classification","name":"Binary Classification","papers":11},{"task":"/task/clustering","name":"Clustering","papers":11}],"tasks_shown":20,"n_tasks":256,"usage_by_year":[{"year":"2017","papers":2},{"year":"2018","papers":2},{"year":"2019","papers":18},{"year":"2020","papers":29},{"year":"2021","papers":71},{"year":"2022","papers":74},{"year":"2023","papers":94},{"year":"2024","papers":161},{"year":"2025","papers":99}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/shap"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}