Fairness Without Imputation: A Decision Tree Approach for Fair Prediction With Missing Values

Fairness Without Imputation: A Decision Tree Approach for Fair Prediction With Missing Values

Explore a 35-minute conference talk by Haewon Jeong from UC Santa Barbara, presented at the Simons Institute, addressing the challenge of fair prediction with missing values in machine learning. Delve into a novel decision tree approach that achieves fairness without relying on imputation techniques. Learn how this method contributes to the field of information-theoretic methods for trustworthy machine learning, offering insights into maintaining fairness in predictive models when dealing with incomplete data sets.