An artificially generated dataset was used to generate data of the form (x, 2x + 55 + e), where e is a normally distributed noise with mean zero and variance 1. Three regression models have been created to fit the data – linear, a degree-15 polynomial and a higher degree polynomial which passes through all the training points as shown in the figure below.

So far you have understood the different principles of model selection. But how do you choose between different models for a given business problem? This is done by comparing the performance 0f these models using different evaluation metrics. Let’s now understand the basics of different evaluation metrics available for both classification and regression problems.