Birhanu Eshete is an Associate Professor of Computer Science at the University of Michigan, Dearborn. His main research focus is in trustworthy machine learning with emphasis on security, safety, privacy, interpretability, fairness, and the dynamics thereof. He also studies online cybercrime and advanced and persistent threats (APTs).

Everything about class-imbalanced/long-tail learning: papers, codes, frameworks, and libraries | 有关类别不平衡/长尾学习的一切：论文、代码、框架与库

Code and Data for NAACL 2024 paper: Fair Abstractive Summarization of Diverse Perspectives

An in-depth performance profiling library for machine learning models

Supporting material for the EuADS Summer School - A hands-on tutorial on explainable methods for machine learning with Python: applications to gender bias

A controlled environment to play around with various data errors and stages in the ML lifecycle and measure their impact on model fairness and stability.

📝 Implementation of our approach for balancing the utility of the decision maker and the fairness towards the decision subjects for a prediction-based decision-making system

Fair ML in credit scoring: Assessment, implementation and profit implications

Fairness in data, and machine learning algorithms is critical to building safe and responsible AI systems from the ground up by design. Both technical and business AI stakeholders are in constant pursuit of fairness to ensure they meaningfully address problems like AI bias. While accuracy is one metric for evaluating the accuracy of a machine le…

📝 Exploring the gradual (in)compatibility of the fairness metrics independence, separation and sufficiency.

Can we predict how long a patient will be in a hospital with a fair comparison on gender, race and health service areas?

major ideas of the session "Fair Clustering" from the NeurIPS 2019 conference