Clearly, data matters for trading. This category is for questions and discussions about concepts, code examples and new applications related to the chapters Market & Fundamental Data: Sources and Techniques and Alternative Data for Finance: Categories and Use Cases. Relevant topics include:

If you are familiar with ML, you may agree that feature engineering tends to be the most important ingredient for improving predictions. The same holds true for trading with a twist: on the one hand, there is decades of research into factors that drive asset returns and quantitative methods to predict prices; on the other hand, new data sources and ML create new opportunities and require re-evaluating established perspectives.

This category focuses on the end-to-end process of designing, backtesting, and evaluating an ML-driven trading strategy introduced in the chapter The ML4T Workflow: From Model to Strategy Backtesting and used throughout the book. Most importantly, it focuses on discussions of how to prepare, design, run and evaluate a backtest using the Python libraries backtrader and Zipline. Relevant topics include:

One of the goals of this community is to help students and practitioners of ML for trading to find like-minded peers. Post here if you are, for example:

This category focuses on questions and discussions about topics covered in the chapter Portfolio Optimization and Performance Evaluation and beyond, including:

Deep learning has been the hottest ML topic of the last several years with plenty of potential for trading due to its ability to extract signals from alternative data like images and text. This category addresses questions and discussions around the topics covered in Part 4, including:

Ultimately, the goal of building ML models and designing trading strategies is to use them for live trading. This category focuses on questions and discussions around:

News about new research, industry developments, events or other items of interest.

This category covers concepts, code examples and new ideas about the application of fundamental supervised and unsupervised learning algorithms to trading. More specifically, relevant topics are related to Chapters 6-13 in part 2 of the book, namely:

Text data is rich yet unstructured and requires preprocessing so that ML algorithms can extract potential signal. Natural Language Processing (NLP) poses some challenges, but has perhaps been the most dynamic area of ML over the last several years, creating large opportunities for trading applications. This category covers topics and code examples covered in Chapters 14-16 as well as new ideas and use cases, including: