Ernest P. Chan, a physics Ph.D. and a former researcher in machine learning at IBM’s T.J. Watson Research Center, is well known to the quant trading community. He is the author of Quantitative Trading: How to Build Your Own Algorithmic Trading Business and Algorithmic Trading: Winning Strategies and Their Rationale. His most recent effort is Machine Trading: Deploying Computer Algorithms to Conquer the Markets (Wiley, 2017).
In Machine Trading Chan discusses the basics of algorithmic trading, factor models, time-series analysis, artificial intelligence techniques, options strategies, intraday trading and market microstructure, bitcoins, and how algorithmic trading is good for body and soul. Where appropriate, he uses MATLAB code to develop his points.
Chan assumes a working knowledge of linear algebra, statistics, and basic computer science, as well as a familiarity with the financial markets, options in particular. Although he provides exercises at the end of each chapter, his work is not really suitable as a textbook. It is, I believe, best viewed as an overlay to a quant trader’s education.
Chan describes an array of trading strategies, most stemming from the academic literature. Many of these strategies were once profitable but have subsequently deteriorated in performance. (You didn’t really expect Chan, who manages money, to share his “winningest” strategies, did you?) But this isn’t the point. Individual strategies are either examples of the types of strategies that can work in particular markets (for instance, “statistical factors can be more useful for trading in markets where fundamental factors are less important for predictive purposes,” such as the forex market) or illustrative of the process of generating or testing a trading model.
Some of the material Chan presents is relevant only to professional traders with large research budgets. But even individual retail traders can extract nuggets of valuable information from this book—if, that is, they have the necessary background.