Skip to main content
It looks like you're using Internet Explorer 11 or older. This website works best with modern browsers such as the latest versions of Chrome, Firefox, Safari, and Edge. If you continue with this browser, you may see unexpected results.
Fairness and Bias in Machine Learning
Recently, fairness has emerged as a matter of concern within machine learning applications. There have been instances of unintended discrimination that arises as a result if using black box machine learning algorithms to drive decision making. We will provide a brief overview of some common biases that can manifest in the training data and equip you with strategies to identify them and evaluate their effects.
This is the presentation that was used in the workshop. There are embedded links in the presentation for you to be able to navigate to the webpages shown during the workshop.
The data files that were used during the workshop. Place these files in your google drive under the folder name 'data' to be able to run the notebook above.