Getting explanations for predictions made by black box models.
-
Updated
Jan 24, 2021 - Jupyter Notebook
Getting explanations for predictions made by black box models.
ML implementations in Multi-scale model for lignin biosynthesis in Populus Trichocarpa
XGB - SHAP XAI
Review of Hassan Sozen (1997) Priority Index for Rapid Assessment of Earthquake Vulnerability in Low Rise RC Structures.
Implementation of the algorithm described in the paper "An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Data"
Using a Kaggle dataset, customer personality was analysed on the basis of their spending habits, income, education, and family size. K-Means, XGBoost, and SHAP Analysis were performed.
Predicting NBA game outcomes using schedule related information. This is an example of supervised learning where a xgboost model was trained with 20 seasons worth of NBA games and uses SHAP values for model explainability.
In this project we predict credit card defaults using classification models.
XAI analytics to understand the working of SHAP values
XAI analytics to understand the working of SHAP values
Use machine learning to find out what drives sales and predict sales
Reading list for "The Shapley Value in Machine Learning" (JCAI 2022)
No-code Machine learning (Pre-alpha)
Predict probability of default on credit
credit default prediction app
Android malware detection using machine learning.
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.
Frontend for ShapEmotionsCorrectionAPI
In this repository you will fine explainability of machine learning models.
Add a description, image, and links to the shapley-additive-explanations topic page so that developers can more easily learn about it.
To associate your repository with the shapley-additive-explanations topic, visit your repo's landing page and select "manage topics."