From the course: Python: Working with Predictive Analytics

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Evaluation of predictive models

Evaluation of predictive models - Python Tutorial

From the course: Python: Working with Predictive Analytics

Start my 1-month free trial

Evaluation of predictive models

“

- [Instructor] Now that you've seen how to build a few regression models, we are moving on to the Evaluation section of our roadmap. I'm going to summarize the strengths and weaknesses of each model in this video. So far, we have used R squared as a way of measuring the success scores of the regression models. Please keep in mind that this score by itself is not enough to make decisions. It's recommended to further visualize, combine it with domain knowledge, and do further tests before making a final judgment. Now, let's take a look at each model. Linear regression has an advantage when there's a linear relationship between the independent variables and dependent variable. However, we need to keep in mind that this may become a disadvantage when we do not have a linear relationship between the independent variables and the dependent variable. Polynomial regression can be a strong model when there's a nonlinear relationship between the independent variables and dependent variable. The…

Contents