Introduction of the evaluation metricsΒΆ

Machine learning models rely on optimizing an objective function, by seeking its minimum or maximum. It is important to understand that this objective function is usually decoupled from the evaluation metric that we want to optimize in practice. The objective function serves as a proxy for the evaluation metric.

While other notebooks will give insight about machine learning algorithms and their associated objective functions, we will focus, in this notebook, on the metrics used to evaluate the performance of a predictive model.

Evaluation metric selection will mainly depend on the model chosen to solve our data science problem.