Methods › General › Interpretability › SHAP
Shapley Additive Explanations
SHAP
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Papers archive 2025-07-28
30 shown of 550, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Correlation vs causation in Alzheimer's disease: an interpretability-driven study 11 Jun 2025 · 0 repositories · arXiv:2506.10179
-
Neurosymbolic Artificial Intelligence for Robust Network Intrusion Detection: From Scratch to Transfer Learning 4 Jun 2025 · 0 repositories · arXiv:2506.04454
-
A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations 3 Jun 2025 · 0 repositories · arXiv:2506.03425
-
Predicting Postoperative Stroke in Elderly SICU Patients: An Interpretable Machine Learning Model Using MIMIC Data 2 Jun 2025 · 0 repositories · arXiv:2506.03209
-
Explainable-AI powered stock price prediction using time series transformers: A Case Study on BIST100 1 Jun 2025 · 0 repositories · arXiv:2506.06345
-
A SHAP-based explainable multi-level stacking ensemble learning method for predicting the length of stay in acute stroke 30 May 2025 · 0 repositories · arXiv:2505.24101
-
Interpretable phenotyping of Heart Failure patients with Dutch discharge letters 30 May 2025 · 0 repositories · arXiv:2505.24619
-
Multi-criteria Rank-based Aggregation for Explainable AI 30 May 2025 · 1 repository · arXiv:2505.24612
-
Machine Learning Framework for Characterizing Processing-Structure Relationship in Block Copolymer Thin Films 29 May 2025 · 1 repository · arXiv:2505.23064
-
Document Valuation in LLM Summaries: A Cluster Shapley Approach 28 May 2025 · 0 repositories · arXiv:2505.23842
-
Triple Attention Transformer Architecture for Time-Dependent Concrete Creep Prediction 28 May 2025 · 0 repositories · arXiv:2506.04243
-
MLRan: A Behavioural Dataset for Ransomware Analysis and Detection 24 May 2025 · 1 repository · arXiv:2505.18613
-
Reverse-Speech-Finder: A Neural Network Backtracking Architecture for Generating Alzheimer's Disease Speech Samples and Improving Diagnosis Performance 23 May 2025 · 0 repositories · arXiv:2505.17477
-
Computing Exact Shapley Values in Polynomial Time for Product-Kernel Methods 22 May 2025 · 0 repositories · arXiv:2505.16516
-
Towards Trustworthy Keylogger detection: A Comprehensive Analysis of Ensemble Techniques and Feature Selections through Explainable AI 22 May 2025 · 0 repositories · arXiv:2505.16103
-
CSAGC-IDS: A Dual-Module Deep Learning Network Intrusion Detection Model for Complex and Imbalanced Data 20 May 2025 · 0 repositories · arXiv:2505.14027
-
Explainable AI for Securing Healthcare in IoT-Integrated 6G Wireless Networks 20 May 2025 · 0 repositories · arXiv:2505.14659
-
Explainable Prediction of the Mechanical Properties of Composites with CNNs 20 May 2025 · 0 repositories · arXiv:2505.14745
-
Learning to Adapt to Position Bias in Vision Transformer Classifiers 19 May 2025 · 1 repository · arXiv:2505.13137
-
Machine Learning-Based Prediction of Mortality in Geriatric Traumatic Brain Injury Patients 19 May 2025 · 0 repositories · arXiv:2505.15850
-
BenSParX: A Robust Explainable Machine Learning Framework for Parkinson's Disease Detection from Bengali Conversational Speech 18 May 2025 · 1 repository · arXiv:2505.12192
-
Modeling Aesthetic Preferences in 3D Shapes: A Large-Scale Paired Comparison Study Across Object Categories 18 May 2025 · 0 repositories · arXiv:2505.12373
-
Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAP 16 May 2025 · 1 repository · arXiv:2505.11189
-
Financial Fraud Detection Using Explainable AI and Stacking Ensemble Methods 15 May 2025 · 0 repositories · arXiv:2505.10050
-
SHAP-based Explanations are Sensitive to Feature Representation 13 May 2025 · 1 repository · arXiv:2505.08345
-
Understanding molecular ratios in the carbon and oxygen poor outer Milky Way with interpretable machine learning 13 May 2025 · 0 repositories · arXiv:2505.08410
-
A Computational Approach to Epilepsy Treatment: An AI-optimized Global Natural Product Prescription System 10 May 2025 · 0 repositories · arXiv:2505.09643
-
Deeply Explainable Artificial Neural Network 10 May 2025 · 0 repositories · arXiv:2505.06731
-
Interpretable SHAP-bounded Bayesian Optimization for Underwater Acoustic Metamaterial Coating Design 10 May 2025 · 0 repositories · arXiv:2505.06519
-
Interactive Diabetes Risk Prediction Using Explainable Machine Learning: A Dash-Based Approach with SHAP, LIME, and Comorbidity Insights 8 May 2025 · 0 repositories · arXiv:2505.05683
Tasks archive 2025-07-28
20 shown of 256 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Feature Importance | 88 |
| Explainable Artificial Intelligence (XAI) | 73 |
| Explainable artificial intelligence | 72 |
| Decision Making | 59 |
| BIG-bench Machine Learning | 42 |
| feature selection | 23 |
| Interpretable Machine Learning | 22 |
| regression | 22 |
| Management | 21 |
| Prediction | 20 |
| Time Series | 19 |
| counterfactual | 18 |
| Fairness | 16 |
| Anomaly Detection | 14 |
| Classification | 14 |
| Diagnostic | 14 |
| Benchmarking | 13 |
| Transfer Learning | 12 |
| Binary Classification | 11 |
| Clustering | 11 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections