In this chapter, we worked on the last project of this entire book, predicting stock (specifically stock index) prices using machine learning regression techniques. We started with a short introduction to the stock market and factors that influence trading prices. To tackle this billion dollar problem, we investigated machine learning regression, which estimates a continuous target variable, as opposed to discrete output in classification. We followed with an in-depth discussion of three popular regression algorithms, linear regression, regression tree and regression forest, and SVR as well as neural networks. We covered the definition, mechanics, and implementation from scratch and with several popular frameworks including scikit-learn, tensorflow, and keras, along with their applications on toy datasets. We also learned the metrics used to evaluate a regression model. Finally, we applied what we learned in this whole chapter to solve our stock price prediction problem.

At last, recall that we briefly mentioned several major stock indexes besides DJIA. Is it possible to better the DJIA price prediction model we just developed by considering historical prices and performance of these major indexes? It's highly likely! The idea behind this is that no stock or index is isolated and that there are weak or strong influences between stocks and different financial markets. This should be intriguing to explore.

In the next and final chapter, we'll wrap up this book with best practices of real-world machine learning. It aims to foolproof your learning and get you ready for the entire machine learning workflow and productionization.