Fairness in machine learning

Our December Meetup will be a remote gathering; the Zoom link will be posted the week of the event.

As machine learning models play an increasingly important role in decision-making, the ways in which these systems can behave unfairly have garnered more attention. The reasons behind this unfairness are many: societal biases reflected in training data, flawed sampling approaches, inherent characteristics of machine learning algorithms themselves, or improper application of model outputs, to name a few. In recent years, a growing body of research has proliferated with the aim of making sense of—and addressing—these harms. This talk will give a high-level introduction to machine learning fairness through an applied example using the tidymodels R packages.