moDel Agnostic Language for Exploration and eXplanation

Workshop: Explanation and exploration of machine learning models with R and DALEX at eRum 2020

Documentation for the DALEX project

examples for modelDown, package that turns model into HTML pages

Efficient and accurate explanation estimation with distribution compression (ICLR 2025 Spotlight)

This is a repository for reproducibility purposes. In this research, a large number of datasets were used to create different ML models, which were then explained by XAI measures. Seeking to identify situations where XAI measures agreed or disagreed with each other.

🔒 Privacy-first Chrome extension to clean history, cookies, and cache — with one click. Lightweight, open source, no tracking.

Robustness of Global Feature Effect Explanations (ECML PKDD 2024)

Building binary predictors on a heavily imbalanced dataset - exercise on policy cross-selling [kaggle]

Multi-class classification of drug resistance in MTB clinical isolates

This is a repository for reproducibility purposes. In this research, a large number of datasets were used to create different ML models, which were then explained by XAI measures. Proposing a new measure of XAI called eXirt.

⏰⚾ Test: DALEX package and modelDown

Elements of my term paper in Data Mining 2 at Faculty of Mathematics, University of Belgrade.

EMA (Exploratory model analysis) case study. Predicting credit card customers behaviour.

A data science summer project with James Bond movies data.

This project predicts whether an individual earns more than 50K using the Adult Income dataset. A Random Forest model is trained and evaluated, with explanations provided through DALEX and LIME for feature importance and model transparency.