Statistically Sound Indicators For Financial Market Prediction: Algorithms in C++

by Timothy Masters

In my decades of professional experience as a statistical consultant in the field of financial market trading, the single most important lesson that I’ve learned about trading is this: the quality of the indicators is vastly more important than the quality of the trading algorithm or predictive model. If you are sloppy about your indicator computation, no high-tech model or algorithm is going to bail you out. Garbage in, garbage out still rules.

This book presents numerous traditional and modern indicators that have been shown to carry significant predictive information. But it will do far more than just that. In addition to a wealth of useful indicators, you will see the following issues discussed:

-->There are simple tests that let you measure the potential information-carrying capacity of an indicator. If your proposed indicator fails this information-capacity test, you should consider revising it. This book describes simple transformations that raise the information-carrying capacity of your indicators and make them more useful for algorithmic trading.

-->You will learn how to locate the regions in your indicator’s domain where maximum predictive power occurs so that you can focus on these important values.

--> You will learn how to compute statistically sound probabilities to help you decide whether the performance of an indicator is legitimate or just the product of random good luck.

--> Most traditional indicators examine one market at a time. But you will learn how examining pairs of markets, or even large collections of markets simultaneously, can provide valuable indicators that quantify complex inter-market relationships.
--> Govinda Khalsa devised a powerful indicator called the Follow-Through Index which reveals how likely it is that an existing trend will continue. This indicator is extremely useful to trend-following traders, but due to its complexity it is not widely employed. This book presents its essential theory and implementation in C++.

--> Gary Anderson developed a detailed and profound theory of market behavior that he calls The JANUS Factor. This theory enables computation of several powerful indicators that tell us, among other things, when trading opportunities are most likely to be profitable and when we should stay out of the market. This book provides the fundamental theory behind The JANUS Factor along with extensive C++ code.

Whether you compute a few indicators and trade by watching their plots on a computer screen, or do simple automated algorithmic trading, or employ sophisticated predictive models, this book provides tools that help you take your trading to a higher, more profitable level.

Genres: Finance

393 pages, Paperback

First published October 22, 2019

About the author

Timothy Masters received a PhD in mathematical statistics with a specialization in numerical computing. Since then he has continuously worked as an independent consultant for government and industry. His early research involved automated feature detection in high-altitude photographs while he developed applications for flood and drought prediction, detection of hidden missile silos, and identification of threatening military vehicles. Later he worked with medical researchers to develop computer algorithms for distinguishing between benign and malignant cells in needle biopsies. For the last twenty years he has focused primarily on automated financial market trading systems. He has authored numerous books on practical applications of neural networks and on developing and testing automated market trading systems.

In addition to his technical work, Timothy Masters is the author of two novels. Red Dust and Bones draws on his scientific background to create a hard-science-fiction mystery about humanity's first outpost on Mars and a discovery that could change our understanding of life itself. His other novel, Ixinia, ventures into fantasy.

Reviews

[Socrates231]

The sections about Entropy and Mutual Information are interesting, the rest not so much