Summary

In this chapter, we learned about ensemble learning and how it can be used in the real world. We discussed decision trees and how to build a classifier based on it.

We learned about random forests and extremely random forests, which are created from ensembling multiple decision trees. We discussed how to build classifiers based on them. We understood how to estimate the confidence measure of the predictions. We also learned how to deal with the class imbalance problem.

We discussed how to find the most optimal training parameters to build the models using grid search. We learned how to compute relative feature importance. We then applied ensemble learning techniques to a real-world problem, where we predicted traffic using an extremely random forest regressor.

In the next chapter, we will discuss unsupervised learning and how to detect patterns in stock market data.