High-performance Algorithmic Trading using Machine LearningКНИГИ » ПРОГРАММИНГ
Название: High-performance Algorithmic Trading using Machine Learning: Building automated trading startegies with AutoML and feature engineering Автор: Franck Bardol Издательство: BPB Publications Год: 2025 Страниц: 398 Язык: английский Формат: epub (true) Размер: 49.3 MB
Machine Learning is not just an advantage; it is becoming standard practice among top-performing trading firms. As traditional strategies struggle to navigate noise, complexity, and speed, ML-powered systems extract alpha by identifying transient patterns beyond human reach. This shift is transforming how hedge funds, quant teams, and algorithmic platforms operate, and now, these same capabilities are available to advanced practitioners.
This book is a practitioner’s blueprint for building production-grade ML trading systems from scratch. It goes far beyond basic return-sign classification tasks, which often fail in live markets, and delivers field-tested techniques used inside elite quant desks. It covers everything from the fundamentals of systematic trading and ML's role in detecting patterns to data preparation, backtesting, and model lifecycle management using Python libraries. You will learn to implement supervised learning for advanced feature engineering and sophisticated ML models. You will also learn to use unsupervised learning for pattern detection, apply ultra-fast pattern matching to chartist strategies, and extract crucial trading signals from unstructured news and financial reports. Finally, you will be able to implement anomaly detection and association rules for comprehensive insights.
This book is designed as a hands-on journey through the key techniques of Machine Learning applied to real-world trading. It starts with the foundations of algorithmic strategy design, then progressively expands into supervised learning, unsupervised models, pattern mining, NLP for financial text, and ends with portfolio construction using advanced ML techniques. The focus is entirely practical—mathematical derivations have been intentionally excluded in favor of code, tools, and examples—making the material accessible without sacrificing technical depth.
You will learn how to apply quantamental methods by integrating accounting data into predictive models, detect structural changes in time series and extract rules automatically, work with alternative and unstructured data, and engineer features that go far beyond basic OHLC inputs, filter out market noise while preserving signal, and construct volume- or volatility-based bars and leverage recent breakthroughs in AutoML and low-code ML, using tools like H2O and Microsoft FLAML. Each chapter combines clear explanations, ready-to-run code, and use cases that reflect real trading problems and constraints.
By the end of this book, you will be ready to design, test, and deploy intelligent trading strategies to institutional standards.
What you will learn: - Build end-to-end machine learning pipelines for trading systems. - Apply unsupervised learning to detect anomalies and regime shifts. - Extract alpha signals from financial text using modern NLP. - Use AutoML to optimize features, models, and parameters. - Design fast pattern detectors from signal processing techniques. - Backtest event-driven strategies using professional-grade tools. - Interpret ML results with clear visualizations and plots.
Who this book is for: This book is for robo traders, algorithmic traders, hedge fund managers, portfolio managers, Python developers, engineers, and analysts who want to understand, master, and integrate Machine Learning into trading strategies. Readers should understand basic automated trading concepts and have some beginner experience writing Python code.
Скачать High-performance Algorithmic Trading using Machine Learning