Simulating Biases for Interpretable Fairness in Offline and Online Classifiers
By: Ricardo Inácio , Zafeiris Kokkinogenis , Vitor Cerqueira and more
Potential Business Impact:
Makes computer decisions fair, even with bad data.
Predictive models often reinforce biases which were originally embedded in their training data, through skewed decisions. In such cases, mitigation methods are critical to ensure that, regardless of the prevailing disparities, model outcomes are adjusted to be fair. To assess this, datasets could be systematically generated with specific biases, to train machine learning classifiers. Then, predictive outcomes could aid in the understanding of this bias embedding process. Hence, an agent-based model (ABM), depicting a loan application process that represents various systemic biases across two demographic groups, was developed to produce synthetic datasets. Then, by applying classifiers trained on them to predict loan outcomes, we can assess how biased data leads to unfairness. This highlights a main contribution of this work: a framework for synthetic dataset generation with controllable bias injection. We also contribute with a novel explainability technique, which shows how mitigations affect the way classifiers leverage data features, via second-order Shapley values. In experiments, both offline and online learning approaches are employed. Mitigations are applied at different stages of the modelling pipeline, such as during pre-processing and in-processing.
Similar Papers
Beyond Internal Data: Constructing Complete Datasets for Fairness Testing
Machine Learning (CS)
Tests AI for fairness without private data.
Software Fairness Dilemma: Is Bias Mitigation a Zero-Sum Game?
Machine Learning (CS)
Makes AI fairer without hurting anyone's performance.
Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
Machine Learning (CS)
Fixes AI's unfairness when it makes new data.