Year: 2020
Type: article
Abstract: In this paper, we study the prevalence of bias in machine learning; we explore the life cycle phases where bias is potentially introduced into a machine learning model; and lastly, we present how adversarial learning can be leveraged to measure unwanted bias and unfair behavior from a machine learning algorithm. This study focuses particularly on the topics of age bias in predicting employee attrition and presents a practical approach for how adversarial learning can be successful in mitigating age bias. To measure bias, we calculate group fairness metrics across five-year age groups and evaluate fairness between a baseline predictive model and an adversarial model. Comparing the fairness metrics of demographic parity and equality of odds, as well as model accuracy, the adversarial model demonstrates a definite improvement on the demographic parity measurement across all age groups in relation to the baseline model.
Source: SMU Data Science Review
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W3087384903
