Methods › General › Interpretability › SHAP

Shapley Additive Explanations

SHAP

550 papers tagged archive 2025-07-28

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.

Source: A Unified Approach to Interpreting Model PredictionsSee Code · slundberg/shap

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 17 in the graph, strongest link: mentioned in the paper). The lookup matched a different name in Syntology's graph, 'SHAP (SHapley Additive exPlanations)' (resolution: alias); this answer is about that name. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:1705.07874) is about this method is not checked.

Origin paper of this answer, arXiv:1705.07874 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 8 harvested samples) · 6 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 550 · with a code link: 175 · where Syntology ran a sample: 26 (19 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (26 of 550 tagged: 19 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument)

Page 1 of 6: papers 1 to 100 of 550, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

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.

TaskPapers
Feature Importance88
Explainable Artificial Intelligence (XAI)73
Explainable artificial intelligence72
Decision Making59
BIG-bench Machine Learning42
feature selection23
Interpretable Machine Learning22
regression22
Management21
Prediction20
Time Series19
counterfactual18
Fairness16
Anomaly Detection14
Classification14
Diagnostic14
Benchmarking13
Transfer Learning12
Binary Classification11
Clustering11

Usage over time archive 2025-07-28

Papers per year tagged with SHAP: 2017 to 2025, peak 161 161 0 2017: 2 papers 2017 2018: 2 papers 2018 2019: 18 papers 2019 2020: 29 papers 2020 2021: 71 papers 2021 2022: 74 papers 2022 2023: 94 papers 2023 2024: 161 papers 2024 2025: 99 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (550 dated). Bars are counts, not a trend claim.

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

Interpretability

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