Evaluating model performance

Evaluation is an essential step in any machine learning model development, as it is the method that allows us to assess whether the models we use are usable or require further improvement.

To evaluate the model’s performance, we need to understand the metrics that can be used to quantify it and assess them based on those numbers. While numerous metrics are available, we will focus on a select few that are suitable for general use cases.

Let’s start with the regression metrics.

Regression metrics

As we use the regression model to predict numerical output, the regression metrics aim to quantify the error between the predicted and actual values, thereby understanding our model’s performance.

For example purposes, we will use the following code to simulate the prediction from the linear regression model:

from sklearn.linear_model import LinearRegression
X = salary[['YearsExperience', 'EducationLevel...