Quantitative Finance Stack Exchange is a question and answer site for finance professionals and academics. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I did check the related posts, like this one here.

However, given if one already has knowledge in finance, machine learning and statistics, and wants to know something more advanced on machine learning based trading rather than the introductory. What would you recommend?

I am looking for anything related: excellent books, research papers, posts, authors, as long as it is related to machine learning and trading in general, but the thing is, really looking for the sources with quality content rather than the ads sites.

share|improve this question
I'm afraid that the more elaborate it is, the more secret it's gonna be kept. But interesting "question" (it's not really a precise question but I wouldn't close it). – SRKX Sep 27 '11 at 13:05
Hi SRKX, indeed. Totally agree with you that in such a field, the more elaborate, there will be more secrets. This is also one of the reasons for me to raise this question here -- to gain more insights from this professional and helpful environment given the fact there is really nothing too much you can gain from Google. :) – Flake Sep 27 '11 at 13:12
Hi Flake, welcome to quant.SE and thanks for posting your question. I would agree that the difficulty of googling for a topic makes it a perfect fit for this site. @SRKX certainly has a point that the more elaborate stuff will be kept secret, but it is certainly possible that good stuff of an advanced nature is out there, and I hope some others here can help you find it. – Tal Fishman Sep 27 '11 at 13:21
Hi Tal, thanks for the warm welcome. It is indeed a nice atmosphere here. – Flake Sep 27 '11 at 13:37
@Flake: You can accept one of the answers if you are satisfied by it :-) – vonjd Jan 28 '13 at 16:02

Stanford University has a free online course in machine learning with video lectures, problem sets, and even a promise of online help with coursework from Stanford faculty.

This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). (iv) Reinforcement learning. The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.

It does not appear as of yet that trading is one of the applications they intend to cover, but you never know...

share|improve this answer
Indeed this course by Professor Andrew Ng is quite nice for anyone who's interested in ML. ;) – Flake Oct 11 '11 at 17:02
This course is outstanding. It's a great way to gain experience with Machine Learning. – B Seven Nov 26 '11 at 3:01
Yes, Prof. Ng is really a great teacher and the whole concept and execution is just great! – vonjd Dec 7 '11 at 17:31
I'm taking this course now. It's hard. But already I see how ML can be applied to stock trading, using Supervised Learning. I think a lot of people want a magic Unsupervised Learning algorithm, but that's not realistic IMO. – user1046685 Jan 22 '12 at 5:04

As the others have already mentioned, this is a very broad question.

Anyway, as a starting point there are some blogs that come to my mind that have some up to date high quality content on these issues from time to time:

share|improve this answer

I think R's CRAN Task Views on Machine Learning is an excellent resource for beginners moving to advanced algorithm traders. It is well-structured, broad, up-to-date, and ready-to-use!


I believe all advanced quantitative traders already know this. But I haven't seen anyone post it here and Flake's related post.

share|improve this answer
+1. Welcome to the site and thank you for the contribution. – olaker Sep 29 '11 at 21:07
Thank you for the warm welcome! I am glad to find this site. – Branson Sep 29 '11 at 21:13

From this site's perspective, I think nothing would be better than a ML.SE. Finally, we got one awhile ago.

UPDATE: Unfortunately, Machine Learning is merging into Cross Validated. To learn more detail, click here."

I have no idea why SE admin was rush to merge ML into CrossValidated. Not a fan of it (Orz). I personally prefer a separate site.

FYI, http://metaoptimize.com/qa/ is also a great Q&A community for ML, but I do hope we can have our own party room on SE. :)

share|improve this answer
Machine learning is in scope on cross validated: stats.stackexchange.com. So this other site is redundant. – Shane Feb 20 '12 at 18:06
@Shane: Well, not everyone thinks so? :) If you are interested, check out the following link. There are various reasons why people prefer a separate ML.SE. I am with them. meta.machinelearning.stackexchange.com/questions/24/… – 楊祝昇 Feb 20 '12 at 18:18
@Shane: Actually, the same analogy applies here. We wouldn't think QF.SE is redundant because QF is in the scope of money/investment/finance, or we would shut down this site once a site of broader topic launch, would you? But I totally understand people outside this community might think in this way. I guess how ML.SE people feel about their community is just like our feelings toward this site. :) – 楊祝昇 Feb 20 '12 at 18:27

In 2010 Informs and Kaggle organized time series prediction contest. The methods used by competitors are described here.

share|improve this answer

There is another artificial intelligence online course co-sponsored by Stanford http://www.ai-class.org/ The class is about to finish, but you can login as a visitor to access the lecture video and handouts.

share|improve this answer
Hi, welcome to quant.SE. Great link! These online Stanford classes look like really great structured introductions to some broadly relevant fields. – Tal Fishman Dec 6 '11 at 22:47
Thanks for warm welcome! – Heavywood Dec 7 '11 at 21:49

These 2 sites are relevant: - The Whole Street (research aggregation) - Oxford Capital Strategies (strategy reviews)

share|improve this answer

I think applying ML techniques to Finance is a work in progress and here are my arguments:

  1. Things like fraud detection are already implemented using ML (personal experience). It should be possible to train a classifier that would tell you when to (or not to) trade.

  2. Have a look at this site http://www.kaggle.com/, from time to time you will find financial related competitions (another indication of the work in progress).

  3. Big players are getting engaged into this game with commercial products:

share|improve this answer

Your Answer


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.