Data-driven decision making entails the risk of discrimination towards specific individuals or population segments defined upon protected attributes like gender, race etc. The domain of fairness-aware machine learning has recently emerged to address the issues of fairness and discrimination in Machine Learning. In particular, methods have been proposed that focus on understanding bias at the data and/or model results, mitigate bias at different phases of the data analysis pipeline from training data to learning algorithms and model outputs as well as accounting for bias via bias-aware data collection, explaining model results etc.

In this project, we will investigate the sources of bias as well as methods for bias detection and mitigation in methods for the learning analytics domain, from traditional classroom data to MOOC data. We will focus in particular on data from the STEM domain, especially Physics.