Machine Trading: Deploying Computer Algorithms to Conquer the Markets

by Ernest P. Chan

Dive into algo trading with step-by-step tutorials and expert insight Machine Trading is a practical guide to building your algorithmic trading business. Written by a recognized trader with major institution expertise, this book provides step-by-step instruction on quantitative trading and the latest technologies available even outside the Wall Street sphere. You'll discover the latest platforms that are becoming increasingly easy to use, gain access to new markets, and learn new quantitative strategies that are applicable to stocks, options, futures, currencies, and even bitcoins. The companion website provides downloadable software codes, and you'll learn to design your own proprietary tools using MATLAB. The author's experiences provide deep insight into both the business and human side of systematic trading and money management, and his evolution from proprietary trader to fund manager contains valuable lessons for investors at any level.

Algorithmic trading is booming, and the theories, tools, technologies, and the markets themselves are evolving at a rapid pace. This book gets you up to speed, and walks you through the process of developing your own proprietary trading operation using the latest tools.

Utilize the newer, easier algorithmic trading platforms Access markets previously unavailable to systematic traders Adopt new strategies for a variety of instruments Gain expert perspective into the human side of trading The strength of algorithmic trading is its versatility. It can be used in any strategy, including market-making, inter-market spreading, arbitrage, or pure speculation; decision-making and implementation can be augmented at any stage, or may operate completely automatically. Traders looking to step up their strategy need look no further than Machine Trading for clear instruction and expert solutions.

Genres: Finance

256 pages, Kindle Edition

Published December 29, 2016

Reviews

[Robert · Rating 2 out of 5]

This book is a hard pass from me. I say this as someone who is a fan of Ernie Chan, and his previous book Algorithmic Trading in particular. By his own admission, Machine Trading was an excuse for Chan to learn about new topics and it really shows. Rather than providing a clear exposition of battle-hardened techniques that he has used successfully, as in Algorithmic Trading, Machine Trading is a medley of basic techniques applied in rather naive ways.

The time series chapter literally puts asset prices into ARIMA models. The volatility chapter uses GARCH to trade volatility (seemingly realising the importance of implied volatility as an afterhtought). The machine learning chapter has the quality of analysis one expects from one of those medium blog posts applying LSTMs to stock prices. The last chapter, titled “Algorithmic Trading is Good for the Body and Soul” is bizarre… he is trying to pitch the benefits of being an independent algo trader, including such sage advice as:

Algorithmic trading is also a good way to improve your health. Research has found that having a bad boss is harmful to one’s health and longevity (Porath, 2015), and furthermore, time spent with any boss (not just bad bosses) is the top-most reason for unhappiness (Kahneman, 2011). As an independent algorithmic trader, you can escape from boss-related unhappiness.

The only redeeming feature of the book, which is why I’ve given it two stars instead of one, is that he provides code for all his ideas and is generally intellectually honest about their failure.

Below is a short summary of resources I would recommend instead of each chapter of this book:

- 1 - Basics of algorithmic trading: Chan’s other book, Algorithmic Trading
- 2 - Factor models: Advanced Portfolio Management, the Barra handbook, Grinold and Kahn.
- 3 - Time-series analysis: literally any intro econometrics course
- 4 - AI techniques: literally any ML book (Intro to Statistical Learning etc).
- 5 - Options strategies: any of Sinclair’s books (e.g. Volatility Trading)
- 6 - Intraday trading: this was the only chapter that wasn’t terrible. But still, any JP Bouchaud paper would be a better intro.
- 7 - “Bitcoins”: just go on cryptotwitter.
- 8 - “Algorithmic trading is good for body and soul”: go outside and touch grass

[Franta · Rating 4 out of 5]

Machine Trading book is an excellent introduction to algorithmic trading. This book is slightly more advanced than Chan's previous two books but it is clearly written and very readable.
To get most of this book the reader would benefit from the knowledge of linear algebra, computer programming (scripting), and how the stock market works.

As usual the book is accompanied by MATLAB scripts. But beware, the scripts are learning examples, not code you should deploy into production without substantial backtesting.

[Kem Bong · Rating 5 out of 5]

I really like Chan's way of teaching, his book is basic but guide you step by step toward Machine Learning, basic but still very useful. There are many good bits in his book, and as he said: in trading, complexity doesn't pay. So he stick with simple model but avoid overfitting. I will re-read his book from time to time to remind me of "sticking to the basic". It is very easy to slap a hundred layers neural network with thousand of nodes per layer, but do you have enough data for that network. Chan used 1 node per layer, yes 1 node :)) and even there he worries he is overfitting because he doesn't have enough data. Learn that from him. Get more uncorrelated data before trying any fancy techniques. It is a 4* content but a 5* writting style (self-contain, easy to understand and follow).

[Auro H A R Pontes · Rating 4 out of 5]

Good information if you’re motivated enough to do your research

this is a good book if you do your homework. People here giving bad reviews think the author will give his full blown strategies for free - nobody does that.

As with any book in this subject, it adds up to your knowledge but you still need to do the hard work.

It does lack some depth though and I wish he could give some more information on cryptocurrencies - this chapter is pretty vague.

Overall a good book.

[Hossein Jar. · Rating 5 out of 5]

A great introduction to basic strategies of algorithmic trading, Chan has discussed about all you need to know. you should have some programming and mathematical bacground to use this book. the codes are done by Matlab

[Hüseyin Çötel · Rating 4 out of 5]

I don't know what to say really there are some not really good chapters but I learned few things especially related with different market orders and how do they operate. I will probably forgot but I know I can learn again from here.

[Tom · Rating 4 out of 5]

Introductory.

[Ryan Negron · Rating 2 out of 5]

Very exclusive of one of the most powerful open source programs to conduct any of this research: Python. When explaining some of the hold out, bagging, and cross validation strategies, there seems to be an over-site of the potentials for data leakage during any sort of time series analysis, but it is overly possible I fell asleep mid read and missed the part where it was covered.

[Jovany Agathe · Rating 4 out of 5]

Machine Trading had a ton of useful information for me. The first chapter looked at data sources for back-testing trading strategies. There was information about which are the best sites to get data from, which have good APIs, and the costs of these services. It was easy to see that the author had worked with lots of different types of data and vendors.

The next few chapters look at analysis using MATLAB as the programming language. The code snippets are well described and fairly easy to understand or translate to another language.