Comments on: Stanford machine learning lectures and POMDP http://www.quantisan.com/stanford-machine-learning-lectures-pomdp/ I am a data scientist and algorithmic trader. Nice to meet you! Wed, 01 Feb 2012 19:51:00 +0000 hourly 1 http://wordpress.org/?v=3.3.1 By: Departed TradeStation and going the Ninja Trader path | Quantisan Systems http://www.quantisan.com/stanford-machine-learning-lectures-pomdp/#comment-816 Departed TradeStation and going the Ninja Trader path | Quantisan Systems Fri, 27 May 2011 18:41:37 +0000 http://traderpau.wordpress.com/?p=426#comment-816 [...] I have the luxury of not tasked to yield results and is free to play with what I want. Including my POMDP discussion in my previous post, and my other idea of using modern control theory (my study focus back in the days) to identify [...] [...] I have the luxury of not tasked to yield results and is free to play with what I want. Including my POMDP discussion in my previous post, and my other idea of using modern control theory (my study focus back in the days) to identify [...]

]]> By: Paul http://www.quantisan.com/stanford-machine-learning-lectures-pomdp/#comment-593 Paul Thu, 23 Dec 2010 18:49:43 +0000 http://traderpau.wordpress.com/?p=426#comment-593 @Yuan, thanks for the link! I'll check it out once I'm back to work. I haven't applied any complex ML technique for a couple of years because I'm now leaning toward using transparent methods. @Yuan, thanks for the link! I’ll check it out once I’m back to work. I haven’t applied any complex ML technique for a couple of years because I’m now leaning toward using transparent methods.

]]> By: Yuan Zhang http://www.quantisan.com/stanford-machine-learning-lectures-pomdp/#comment-590 Yuan Zhang Thu, 23 Dec 2010 03:18:10 +0000 http://traderpau.wordpress.com/?p=426#comment-590 Paul, See if you are interested in <a href="http://delivery.acm.org/10.1145/1780000/1774585/p2394-baffa.pdf?key1=1774585&key2=0000603921&coll=DL&dl=ACM&CFID=3111716&CFTOKEN=29110117" rel="nofollow">this paper </a> , which described a POMDP model to analyze stock investing policies. Paul,

See if you are interested in this paper , which described a POMDP model to analyze stock investing policies.

]]> By: Yuan Zhang http://www.quantisan.com/stanford-machine-learning-lectures-pomdp/#comment-587 Yuan Zhang Wed, 22 Dec 2010 22:29:46 +0000 http://traderpau.wordpress.com/?p=426#comment-587 Hi Paul, It was a great read about your post on applying POMDP on financial trading. I have been working on improving POMDP algorithms and applying POMDP on medical decision area in my Ph.D research. Seems like there are very few studies about applying POMDP on trading, but I bet there must be some chance to combine those together. Good luck with your trading! Hi Paul,

It was a great read about your post on applying POMDP on financial trading. I have been working on improving POMDP algorithms and applying POMDP on medical decision area in my Ph.D research. Seems like there are very few studies about applying POMDP on trading, but I bet there must be some chance to combine those together. Good luck with your trading!

]]> By: Benjamin http://www.quantisan.com/stanford-machine-learning-lectures-pomdp/#comment-288 Benjamin Sat, 22 May 2010 18:31:53 +0000 http://traderpau.wordpress.com/?p=426#comment-288 Hi Paul, just discovered your blog. Have been reading your articles with great interest. I haven't heard of POMDP before, but they look interesting. In fact a fast search turns up several studies with <a href="http://scholar.google.com/scholar?hl=en&q=pomdp+stock&btnG=Search&as_sdt=2000&as_ylo=&as_vis=0" rel="nofollow">stocks and POMDP</a>. Just one thing... You write: <blockquote cite="">A drawback with using artificial intelligence in trading is that A.I. are good for closed ended system but bad for open ended ones (i.e. trading). </blockquote> Machine learning (ML) techniques, such as POMDP, (if you say "artificial intelligence", more traditional rule-based systems could be understood) are based on statistical patterns in data, which implies that you don't have to know everything about the system, you just need enough data. Hi Paul,
just discovered your blog. Have been reading your articles with great interest. I haven’t heard of POMDP before, but they look interesting. In fact a fast search turns up several studies with stocks and POMDP.

Just one thing… You write:

A drawback with using artificial intelligence in trading is that A.I. are good for closed ended system but bad for open ended ones (i.e. trading).

Machine learning (ML) techniques, such as POMDP, (if you say “artificial intelligence”, more traditional rule-based systems could be understood) are based on statistical patterns in data, which implies that you don’t have to know everything about the system, you just need enough data.

]]> By: zin http://www.quantisan.com/stanford-machine-learning-lectures-pomdp/#comment-9 zin Thu, 23 Oct 2008 19:54:07 +0000 http://traderpau.wordpress.com/?p=426#comment-9 hello, paul :) nice to read your good post i have reached to your blog while finding pomdp articles i'm trading currency (fx) and i'm trying pomdp way to that as you know, there is various a.i. (many types of neural network , rl ,etc etc) i have studied about that for long time and now i'm trying pomdp , it will works well? i hope so :) good luck for your trading and see you on the market ~ hello, paul :) nice to read your good post
i have reached to your blog while finding pomdp articles
i’m trading currency (fx) and i’m trying pomdp way to that
as you know, there is various a.i. (many types of neural network , rl ,etc etc)
i have studied about that for long time
and now i’m trying pomdp , it will works well?
i hope so :)
good luck for your trading and see you on the market ~

]]>