Popular GitHub Repositories for Shap

A game theoretic approach to explain the output of any machine learning model.

? Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

利用lightgbm做(learning to rank)排序学习，包括数据处理、模型训练、模型决策可视化、模型可解释性以及预测等。Use LightGBM to learn ranking, including data processing, model training, model decision visualization, model interpretability and prediction, etc.

TimeSHAP explains Recurrent Neural Network predictions.

Adversarial Attacks on Post Hoc Explanation Techniques (LIME/SHAP)

Real-time explainable machine learning for business optimisation

Overview of different model interpretability libraries.

IoT Attack Detection with machine learning

This project proposes a novel methodology to automatically learn financial lexicons that outperform the benchmark Loughran-McDonald lexicon in sentiment analysis tasks

A platform that provides users with easy access to AI services developed by Montimage and usage of explainable AI techniques (e.g., LIME, SHAP).

Predicting whether or not a person deposits money after a marketing campaign. Gain insights to develop the best strategy in the next marketing campaign

[Frontiers in AI Journal] Implementation of the paper "Interpreting Vision and Language Generative Models with Semantic Visual Priors"

This notebook is ispired by the AIX360 HELOC Credit Approval Tutorial, which shows different explainability methods for a credit approval process. Here XGBoost is used for classification, achieving better accuracy than most of the models used in that notebook. Then, feature importance methods are shown, to be compared with the Data Scientist explanations methods provided in the above notebook. The first ones come directly with XGBoost and the other is based on SHAP.

Demo of shapely values for interpreting decision tree model

Repository with code for building, evaluating and explaining Dota 2 prediction models for team victory. Submitted to the artifact evaluation track of the 16th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment - AIIDE 2020

Streamlit app repository for Explainable AI application

Using LIME and SHAP for model interpretability of Machine Learning Black-box models.

Is Deleting the Dataset of a Self-Aware AGI ethical? Does It Possess a Soul by Self-Awareness? Assessing the Existence of a Soul and Ethical Implications Using Fuzzy Logic

This repository is created to share the steps that were taken in making my Graduation Thesis for my Applied Statistics Diploma, the project is about creating a machine learning model to predict the churn in a telecom company, this repository includes: The dataset used in the project, the relevant code, and the theisis in pdf.

The goal of SHAP is to explain the prediction of an instance x by computing the contribution of each feature to the prediction. The SHAP explanation method computes Shapley values from coalitional game theory. The feature values of a data instance act as players in a coalition.