Python for Finance, 3rd Edition

Chapter 15. Machine and Deep Learning

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 15th chapter of the final book. Please note that the GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

Machine learning provides a flexible toolkit for finding patterns in data and building predictive models. In quantitative finance you can use the same core ideas—from linear regression and classification to deep neural networks—for tasks ranging from simple signal extraction to complex portfolio or risk models.

This chapter introduces a balanced set of tools. You start with baseline models from scikit-learn for regression and classification on synthetic datasets where you know the ground truth. You then explore unsupervised learning with principal component analysis (PCA) and clustering before building a small PyTorch neural network for non-linear classification. Each section uses visual examples so you can see how model predictions compare to the true labels.

The chapter shows how to frame supervised learning problems on synthetic datasets with known structure, train and evaluate baseline models from scikit-learn, apply PCA and K-means clustering to ...