Designing and executing an ML-driven strategy

In this book, we demonstrate how ML fits into the overall process of designing, executing, and evaluating a trading strategy. To this end, we'll assume that an ML-based strategy is driven by data sources that contain predictive signals for the target universe and strategy, which, after suitable preprocessing and feature engineering, permit an ML model to predict asset returns or other strategy inputs. The model predictions, in turn, translate into buy or sell orders based on human discretion or automated rules, which in turn may be manually encoded or learned by another ML algorithm in an end-to-end approach.

Figure 1.1 depicts the key steps in this workflow, which also shapes the organization of this book:

Figure 1.1: The ML4T workflow

Part 1 introduces important skills and techniques that apply across different strategies and ML use cases. These include the following:

• How to source and manage important...