Hands-On Machine Learning with Scikit-Learn and TensorFlow

by Aurelien Geron

Overview

Published in 2017 by O'Reilly Media, this 564-page book provides a practical, code-first introduction to machine learning and deep learning. While not a trading book per se, it is included in this trading library because machine learning techniques are increasingly applied to algorithmic trading, quantitative finance, and market prediction.

Part I: Fundamentals of Machine Learning

Covers the ML landscape (supervised, unsupervised, semi-supervised, reinforcement learning), end-to-end ML projects, classification, training models (linear regression, polynomial regression, regularization), support vector machines, decision trees, ensemble methods (random forests, gradient boosting), and dimensionality reduction (PCA, kernel PCA).

Part II: Neural Networks and Deep Learning

Covers TensorFlow fundamentals, artificial neural networks, training deep nets (vanishing gradients, batch normalization, dropout), convolutional neural networks (CNNs) for image recognition, recurrent neural networks (RNNs, LSTM, GRU) for sequence modeling, autoencoders for unsupervised feature learning, and reinforcement learning.

Relevance to Trading

The techniques covered have direct applications in finance: regression models for price prediction, classification for trade signal generation, RNNs/LSTMs for time series forecasting, reinforcement learning for portfolio optimization, and ensemble methods for combining multiple alpha signals. The practical, code-based approach makes it accessible to traders who want to implement ML strategies.