Fairness

Estimated module length: 110 minutes

Evaluating a machine learning model (ML) responsibly requires doing more than just calculating overall loss metrics. Before putting a model into production, it's critical to audit training data and evaluate predictions for bias.

This module looks at different types of human biases that can manifest in training data. It then provides strategies to identify and mitigate them, and then evaluate model performance with fairness in mind.

Learning objectives

• Become aware of common human biases that can inadvertently be reproduced by ML algorithms.
• Proactively explore data to identify sources of bias before training a model.
• Evaluate model predictions for bias.

Prerequisites:

This module assumes you are familiar with the concepts covered in the following modules:

• Introduction to Machine Learning
• Linear regression
• Logistic regression
• Classification
• Working with numerical data
• Working with categorical data
• Datasets, generalization, and overfitting

Key terms:

• Bias (ethics/fairness)
• Model