- Paperback: 520 pages
- Publisher: CreateSpace Independent Publishing Platform (June 1, 2013)
- Language: English
- ISBN-10: 148950771X
- ISBN-13: 978-1489507716
- Product Dimensions: 7.4 x 1.2 x 9.7 inches
- Shipping Weight: 2.5 pounds (View shipping rates and policies)
- Average Customer Review: 26 customer reviews
- Amazon Best Sellers Rank: #278,624 in Books (See Top 100 in Books)
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Statistically Sound Machine Learning for Algorithmic Trading of Financial Instruments: Developing Predictive-Model-Based Trading Systems Using TSSB
Use the Amazon App to scan ISBNs and compare prices.
The Amazon Book Review
Author interviews, book reviews, editors picks, and more. Read it now
Frequently bought together
Customers who bought this item also bought
About the Author
David Aronson is a pioneer in machine learning and nonlinear trading system development and signal boosting/filtering. He has worked in this field since 1979 and has been a Chartered Market Technician certified by The Market Technicians Association since 1992. He was an adjunct professor of finance, and regularly taught to MBA and financial engineering students a graduate-level course in technical analysis, data mining and predictive analytics. His ground-breaking book “Evidence-Based Technical Analysis” was published by John Wiley & Sons 2006. --------- 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 current focus is methods for evaluating financial market trading systems. He has authored five books on prediction, classification, and practical applications of neural networks: Practical Neural Network Recipes in C++ (Academic Press, 1993) Signal and Image Processing with Neural Networks (Wiley, 1994) Advanced Algorithms for Neural Networks (Wiley, 1995) Neural, Novel, and Hybrid Algorithms for Time Series Prediction (Wiley, 1995) Assessing and Improving Prediction and Classification (CreateSpace, 2013) More information can be found on his website: TimothyMasters.info
Top customer reviews
There was a problem filtering reviews right now. Please try again later.
The book itself is essentially a manual for the free (with purchase of the book) TSSB software. The TSSB software itself does far more than my personal efforts and does them far more robustly. In terms of raw analysis I think the software is worth the price of the book. It is perhaps even a bargain. Scattered throughout the book/manual is enough descriptive text about the mechanics and algorithms to make this a worthwhile purchase for me. However, it is important to mention that I'm just an amateur. I found it useful others may not.
I would have given the book and software five stars but I took one star off for the following reasons:
1. There is no straightforward way to use modeling results you create in the TSSB software in a real-time trading capacity. No interfaces or exports are available without some clumsy hacks. I will likely be able to code around these limitations because of my software background but this may not be true for everyone. Frankly, this is a big problem (although an understandable one) and I almost took off two stars because of it.
2. The software itself has some rough edges in terms of usability and workflow, although I have not yet come across any bugs. I think it would be better if it treated scripts as if you were working in a standard software development IDE.
3. My initial impression is that the only way to use complicated custom indicators in models is to create those indicators offline and then import them as part of a TSSB database (just a delimited ASCII file). This is more annoying than a problem, since the database format is a simple delimited ASCII file.
I am a data scientist outside finance, and this book helped me transfer some of my knowledge in machine learning to the world of finance. The authors also point out many rookie mistakes people make while preparing their data / trading system. This is a no-BS book that is worth 1000s of dollars. It's not written by marketers but by people who actually trade.
Do yourself a favor, and buy this book.
As a math and finance professional, I find it very difficult to just accept that because the price of a stock goes through a magic line it will go up. I need hard evidence, and this is what TSSB allows the user to do, and this manual is essential in order to be able to learn how to work with the software.
I have already discovered several statistically significant models for predicting price changes in stocks. Not just a model that randomly fits a small data set, a model that is incredibly likely to be successful into the future.
This book and accompanying software has changed how I look at the markets, and since I received my copy a few weeks ago I have not been able to put it (or TSSB) down.
Let me say, however, that this isn't a get rich quick scheme. It is a user guide for a statistically sound tool to build algorithmic based trading models using statistical inference. There is not a better tool, nor instruction manual on the market and it is an absolute must for anyone thinking of trading with algorithms.
I thank the authors for releasing this software and manual and not selling it to Bridgewater or Citadel for several million dollars.
Most recent customer reviews
I, just like you, am on my journey to "Holy Grail".Read more