I'm thinking of trading on either the FX or Stock markets using ML algorithms (primarily neural networks) on an intraday timescale. Does anyone have any experience in doing this? Any tips/stories/recommendations on brokers, data, etc? Is it a complete waste of time to try without being a big fish (I've only got about 10K to venture on this)?
Ask HN: Has anyone used machine learning to trade?
1–10 of 64 posts
Re: Ask HN: Has anyone used machine learning to trade?
#2Is it a complete waste of time to try without being a big fish (I've only got about 10K to venture on this)?
Yes. The intraday movement of stocks is small enough that you'd need to be using a large fraction of your capital on every single trade in order to overcome trading costs; and based on the Kelly criterion you'd need to have unrealistically high odds of betting correctly in order to avoid going broke.
Re: Ask HN: Has anyone used machine learning to trade?
#3Is it a complete waste of time to try without being a big fish (I've only got about 10K to venture on this)? Yes. The intraday movement of stocks is small enough that you'd need to be using a large fraction of your capital on every single trade in order to overcome trading costs; and based on the Kelly criterion you'd need to have unrealistically high odds of betting correctly in order to avoid going broke.
Do you think that interday would be more suitable then?
Re: Ask HN: Has anyone used machine learning to trade?
#4Can't you just download a historical set and use that to test whatever algorithms you think you would use? Then when you are confident enough in their performance, you can take the risk? I wouldn't say it would be a complete waste of time because you would be sure to learn something. If you think you can realistically make money--well then, that's a different question that I wouldn't be fit to answer.
Re: Ask HN: Has anyone used machine learning to trade?
#5Is it a complete waste of time to try without being a big fish (I've only got about 10K to venture on this)? Yes. The intraday movement of stocks is small enough that you'd need to be using a large fraction of your capital on every single trade in order to overcome trading costs; and based on the Kelly criterion you'd need to have unrealistically high odds of betting correctly in order to avoid going broke.
Do you think that interday would be more suitable then?
More suitable, sure. But I still doubt you'd get anywhere -- people who run hedge funds are very much aware of ML techniques, so I'd expect them to run circles around you.
Re: Ask HN: Has anyone used machine learning to trade?
#6If you're interested in this, why not join a firm that does it? They will have a large capital base to start with and eventually start your own venture. Unfortunately 10k won't get you very far in this game
Re: Ask HN: Has anyone used machine learning to trade?
#7Being a "small fish" is actually an advantage since you have less capital you need to put to work and thus can more easily get fills and catch the bigger waves generated by the bigger fish institutions like mutual and hedge funds.
The institutions have to hold on for longer periods and can't really "scalp" trades per se given that the bid/ask volume would collapse if they didn't distribute and "average in" slowly overtime to accumulate a position vs. buying or dumping their entire position all at once.
Re: Ask HN: Has anyone used machine learning to trade?
#8A strange game. The only way to win is not to play.
Re: Ask HN: Has anyone used machine learning to trade?
#9intraday NN is irrelevant because NN are prone to overlearning, so the stuff becomes even more horrible - actually in reality you don't care which way it moves, as long as it moves: this is why the "big fish". It is like owning the place in Vegas: you don't care about the bets (much less about their substance or "direction"), as long as there are bets.
if you really want intraday, think about news.google.com and http://rs2007.limsi.fr/index.php/TLP:Page_12 to automatically tweak the few k base parameters (SVM, associative memory etc).
http://www.bbc.co.uk/science/horizon/1999/midas.shtml
Options, Futures and Other Derivatives, J. C. Hull, Prentice Hall Int’l
Financial Calculus, M. Baxter and A. Rennie, Cambridge University Press
but the ML part is almost irrelevant: it is not the lever in the leverage (think CDO trade).
Re: Ask HN: Has anyone used machine learning to trade?
#10If you're interested in this, why not join a firm that does it? They will have a large capital base to start with and eventually start your own venture. Unfortunately 10k won't get you very far in this game
Practice some with historical data, get a job with a firm that does this, and eventually strike out on your own. If you prove yourself, people will hand you millions to manage. Starting with your own money seems like a bit of a fools game.