Flask app that predicts the risk of heart disease based on a GBT ML model, and shows the confidence in the prediction as well as the factors behind the prediction (explainability).

A project for Intelligent Systems course done in 2019.3, it's a regression model using the XGBoost algorithm to predict future values ​​of investment fund shares.

Save thousands of API calls. Custom model & dataset aiming at predicting a game difficulty score ("lobby avg kd") without calling players' games history stats and profiles.

In this repository you will fine explainability of machine learning models.

Résumé de mes projets de Machine Learning

This repository contains the code for machine learning models designed to predict the outcomes of horse races, with SHAP (SHapley Additive exPlanations) interpretation incorporated for enhanced model interpretability.

Examines fairness metrics for models including gender stereotyping versus group differences due to appropriate predictors. Also explores feature bias mitigation

Analysing Time series and spatiotemporal data

Analytical computation of rolling and expanding Shapley values for time-series data.

Search vector Shapley in cooperative game

Exploratory data analysis, model development and model explainability for the heart disease web application. Stack: Databricks, Pyspark, MLFlow, AutoML, Shapley, Docker.

A solution concept in cooperative game theory

eXplainable Artificial Intelligence - Squeezing LIME in a custom network & SHAPling around a custom network

Interpretable machine learning based on Shapley values

Trained a classifier by using labeled data and oversampling and undersampling techniques to predict if a borrower will default on a loan. The model is intended to be used as a reference tool to help investors make informed decisions about lending to potential borrowers based on their ability to repay. The purpose is to lower risk & maximize profit.

Personal website of Frank Huettner

FastAPI for gathering LocationIQ bounding box and PurpleAir Sensor Data then creating interpolated GeoJson using KNN-Regression

Using data within first 24 hours of intensive care to develop a machine learning model that could improve the current patient survival probability prediction system (apache_4a) and is more generalized to patients outside of the US

An open source library for key drivers analysis based on Shapley values and Kano Theory

This is an official repository for "2D-Shapley: A Framework for Fragmented Data Valuation" (ICML2023).