Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 14 down vote favorite
14

Based on this post, http://quant.stackexchange.com/questions/111/how-can-i-go-about-applying-machine-learning-algorithms-to-stock-markets, I want to digest Elements of Statistical Learning. Fortunately it is available for free and I started reading it.

I don't have enough knowledge to understand it. Can you recommend a book that is a better introduction to the topics in the book? Hopefully something that will give me the knowledge needed to understand it?

Related

How to get an introductory understanding of Machine Learning?

share|improve this question
7  
I found Strang's Linear Algebra and its applications to be extremely useful in understanding the matrix manipulations which form a large part of the elements. – richiemorrisroe Nov 26 '11 at 9:13

5 Answers

up vote 7 down vote accepted

I bought, but have not yet read,

S. Marsland, Machine Learning: An Algorithmic Perspective, Chapman & Hall, 2009.

However, the reviews are favorable and state that it is more suitable for beginners than other ML books that have more depth. Flipping through the pages, it looks to me to be good for me because I have little math background.

share|improve this answer
Looks great - very accessible. – B Seven Nov 26 '11 at 5:38
I downloaded and read the "sample" - all 19 pages (wow). It is much easier to understand than The Elements of Statistical Learning. Definitely seems to be what I am looking for. Thanks. – B Seven Nov 26 '11 at 6:11
2  
I have made edits to your question to provide a citation for the book. Generally speaking, putting things like "I like this one" in an answer is discouraged since if the link breaks, no one will know what "this one" was referring to. Cheers. – cardinal Nov 26 '11 at 16:47
I just got this and started reading it (first 75 pages). It is awesome. Very easy to understand, yet is detailed enough to be practical and useful. Highly recommended for anyone who wants to use Machine Learning. Exactly what I was looking for. Thanks! – B Seven Dec 4 '11 at 21:00
up vote 9 down vote

I found Programming Collective Intelligence the easiest book for beginners, since the author Toby Segaran is is focused on allowing the median software developer to get his/her hands dirty with data hacking as fast as possible.

Typical chapter: The data problem is clearly described, followed by a rough explanation how the algorithm works and finally shows how to create some insights with just a few lines of code.

The usage of python allows one to understand everything rather fast (you do not need to know python, seriously, I did not know it before, too). DONT think that this book is only focused on creating recommender system. It also deals with text mining / spam filtering / optimization / clustering / validation etc. and hence gives you a neat overview over the basic tools of every data miner.

Chapter 10 even deals with stock market data, but the focus is not on time series data mining. Maybe the only drawback (for you) of this excellent book.

share|improve this answer
It's available on Safari Books Online safaribooksonline.com. Thanks. – B Seven Nov 26 '11 at 14:07
1  
Got this book and started working through it. It is very practical. In the first 18 pages you implement a complete (basic) recommendation engine. – B Seven Nov 26 '11 at 15:41
Wow, this book is really incredible. It teaches you how to implement all sorts of Machine Learning algorithms with just a little Python code. One of the most practical books ever. The only drawback is that Python has been updated since the book was published. It also uses many API's which have also changed. So I don't think the examples will work without some tweaking. – B Seven Dec 4 '11 at 21:17
@BSeven thank you, did not know that. I am not sure whether I prefer a book which utilizes pre-existing libraries (which is generally a could thing) or its own code (which works for all book examples but may be less robust due to less users). – steffen Dec 5 '11 at 10:15
I think these days the only choice is pre-existing libraries. They are ubiquitous, easy to integrate, cross-platform, multi-language, and fast. Besides that, if a book has its own code, it is much more difficult to modify. It's easier to modify calls to a library. Thanks for the recommendation. It is a great resource. – B Seven Dec 5 '11 at 14:08
up vote 6 down vote

Introduction to Machine Learning, by E. Alpaydin (MIT Press, 2010, 2nd ed.), covers a lot of topics with nice illustrations (much like Bishop's Pattern Recognition and Machine Learning).

In addition, Andrew W. Moore has some nice tutorials on Statistical Data Mining.

share|improve this answer
(+1) Do not know the book, but the tutorials of Andrew Moore are great (and even entertaining sometimes) – steffen Nov 26 '11 at 11:55
@steffen I'd recommend Radford Neale's Statistical Methods for Machine Learning and Data Mining too. – chl♦ Nov 26 '11 at 12:11
1  
+1 Alpaydin is the right way to go. I was in the exact same situation as the OP a few months ago. Struggling badly with Tibshirani, and then came across Alpaydin and things have been much better since. Eventually though I think Tibshirani is a must read. – Andy Nov 26 '11 at 20:47
The link to Introduction to Machine Learning should be cmpe.boun.edu.tr/~ethem/i2ml2e/index.html – B Seven Nov 28 '11 at 2:52
@BSeven Thanks for updating the link to point to the 2nd edition. – chl♦ Nov 28 '11 at 8:45
up vote 5 down vote

Mayhaps Wasserman's All of Statistics would be of interest. You can sample the book from the link given - and just the first few paragraphs of the preface make a hard sale to your market - and you can likely download the book free through Springer if you are associated with a university.

EDIT: Oops, didn't notice how ancient this thread was.

share|improve this answer
Doesn't matter, the recomendation is still useful for everyone else who reads the thread (like me ;o). – Dikran Marsupial Oct 23 '12 at 16:56
up vote 1 down vote

I'd strongly recommend A First Course in Machine Learning by Rogers and Girolami. It covers the key ideas in a very logical order, with good examples and with the minimum level of maths to have a proper grounding in the fundamentals. It doesn't have the breadth of coverage of some books, but that is exactly why it is so good as an introductory text.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.