Summary

In this chapter, we learned about various techniques of ensemble learning. Let's summarize our learning in this chapter.

At the beginning of the chapter, we were introduced to the concepts of variance and bias and we learned that ensemble learning is a technique that aims to combine individual models to create a superior model, thereby reducing variance and bias and improving performance. To further explore different techniques of ensemble learning, we downloaded the credit card approval dataset. We also fitted a benchmark model using logistic regression.

In the subsequent sections, we were introduced to six different techniques of ensemble learning; three of them being simple techniques and the remaining three being advanced techniques. The averaging method creates an ensemble by combining the predictions of base learners and averaging the prediction probabilities. We were able to get better results than the benchmark model using this technique. The weighted averaging...