Model interpretability and understanding for PyTorch
-
Updated
May 4, 2026 - Python
#
feature-importance
Here are 85 public repositories matching this topic...
XAI - An eXplainability toolbox for machine learning
machine-learning ai evaluation ml artificial-intelligence upsampling bias interpretability feature-importance explainable-ai explainable-ml xai imbalance downsampling explainability bias-evaluation machine-learning-explainability xai-library
-
Updated
Nov 29, 2025 - Python
Leave One Feature Out Importance
-
Updated
Feb 14, 2025 - Python
Shapley Interactions and Shapley Values for Machine Learning
python machine-learning game-theory interpretability feature-importance explainable-ai banzhaf-index shapley interpretable-machine-learning shap explainability feature-attribution feature-interactions shapley-interactions shapiq
-
Updated
May 5, 2026 - Python
Features selector based on the self selected-algorithm, loss function and validation method
data-science machine-learning feature-selection feature-extraction feature-engineering greedy-search feature-importance
-
Updated
May 8, 2019 - Python
ProphitBet is a Machine Learning Soccer Bet prediction application. It analyzes the form of teams, computes match statistics and predicts the outcomes of a match using Advanced Machine Learning (ML) methods. The supported algorithms in this application are Neural Networks, Random Forests & Ensembl Models.
statistics deep-neural-networks neural-network random-forest pandas-dataframe machine-learning-algorithms soccer data-visualization seaborn football-data predictions soccer-matches imbalanced-learning feature-importance soccer-betting optuna feature-analysis imbalanced-learn interpretability-methods upcoming-games
-
Updated
Apr 16, 2026 - Python
This package can be used for dominance analysis or Shapley Value Regression for finding relative importance of predictors on given dataset. This library can be used for key driver analysis or marginal resource allocation models.
feature-selection logistic-regression feature-engineering regression-models predictor multiple-regression feature-importance classification-model relative-importance dominance-analysis r-square shapley-value keydrivers dominance dominance-statistics predictor-importance pseudo-r-square
-
Updated
Aug 17, 2023 - Python
Variance-based Feature Importance in Neural Networks
-
Updated
Jun 28, 2025 - Python
Customer churn prediction with Python using synthetic datasets. Includes data generation, feature engineering, and training with Logistic Regression, Random Forest, and Gradient Boosting. Improved pipeline applies hyperparameter tuning and threshold optimization to boost recall. Outputs metrics, reports, and charts.
python data-science machine-learning random-forest classification logistic-regression predictive-modeling gradient-boosting portfolio-project feature-importance roc-auc customer-analytics precision-recall customer-churn
-
Updated
Sep 11, 2025 - Python
Using / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"
python machine-learning statistics ai random-forest scikit-learn ml artificial-intelligence stats feature-engineering ensemble-model boosting interpretability random-forests feature-importance explainable-ai
-
Updated
Feb 11, 2021 - Python
Predicted and identified the drivers of Singapore HDB resale prices (2015-2019) with 0.96 Rsquare & $20,000 MAE. Web app deployment using Streamlit for user price prediction.
machine-learning random-forest linear-regression data-visualization feature-engineering feature-importance hdb-resale-prices
-
Updated
Dec 27, 2023 - Python
This repository contains the implementation of SimplEx, a method to explain the latent representations of black-box models with the help of a corpus of examples. For more details, please read our NeurIPS 2021 paper: 'Explaining Latent Representations with a Corpus of Examples'.
machine-learning artificial-intelligence neural-networks method interpretability feature-importance explainable-ai latent-space latent-representations neurips example-based-explanations neurips-2021
-
Updated
Jan 31, 2023 - Python
A minimal, reproducible explainable-AI demo using SHAP values on tabular data. Trains RandomForest or LogisticRegression models, computes global and local feature importances, and visualizes results through summary and dependence plots, all in under 100 lines of Python.
python open-source data-science machine-learning random-forest tabular-data data-visualization logistic-regression reproducibility model-interpretation feature-importance classification-model explainable-ai interpretable-machine-learning shap responsible-ai shap-values model-explainability trustworthy-ai model-audit
-
Updated
Nov 9, 2025 - Python
Significance tests of feature relevance for a black-box learner
feature-selection statistical-inference statistical-tests hypothesis-testing feature-importance xai significance-testing black-box-testing image-inference
-
Updated
Aug 2, 2024 - Python
This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human concepts. For more details, please read our NeurIPS 2022 paper: 'Concept Activation Regions: a Generalized Framework for Concept-Based Explanations.
deep-neural-networks deep interpretability feature-importance explainable-ai explainable-ml xai concept-based-explanations
-
Updated
Oct 7, 2022 - Python
A Python Package that computes Target Permutation Importances (Null Importances) of a machine learning model.
-
Updated
Dec 24, 2024 - Python
Toolbox for analysis of model's quality and model's description. For further details see
quality data-science quality-control ai ml data-analysis model-checking predictive-analysis sensitivity predictive-modeling sensitivity-analysis evaluation-metrics prediction-model feature-importance explainable-ai explainable-ml explainability prediction-uncertainty feature-sensitivity lime-explanation
-
Updated
May 6, 2024 - Python
Implementation of various feature selection methods using TensorFlow library.
tensorflow fisher feature-selection feature-extraction tensorflow-experiments tensorflow-library pearson-correlation feature-importance mrmr ttest f-statistics f-test
-
Updated
Nov 21, 2022 - Python
Automated validation toolkit for tabular ML models in finance and regulated domains.
python finance machine-learning tabular-data audit calibration stress-testing fairness data-profiling model-validation no-code feature-importance credit-risk automated-reporting drift-detection explainability regulatory-compliance model-risk-management model-governance tabular-ml
-
Updated
Apr 30, 2026 - Python
Python package for feature ranking
-
Updated
Apr 3, 2026 - Python
Improve this page
Add a description, image, and links to the feature-importance topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the feature-importance topic, visit your repo's landing page and select "manage topics."