News for hackers. Stuff that matters.
Re:How I made $500k with machine learning and high frequency... by pdog on Tuesday November 06, 2012 @10:46AM (#4748868)
Would you be able to open source any of the code behind your trading system? Maybe not the "secret sauce", but it would be interesting to see how you processed the data feeds, modeled the data, entered orders, etc.
Re:How I made $500k with machine learning and high frequency... by jspaulding on Tuesday November 06, 2012 @10:51AM (#4748905)
I certainly could open source it. I may just wait a bit on the off chance that somebody wants to purchase it.
Re:How I made $500k with machine learning and high frequency... by sturadnidge on Tuesday November 06, 2012 @11:32AM (#4749126)
Relax, nobody is buying your program.

Other than sheer luck, the most plausible explanation for your diminishing returns is that you found a strategy that worked _at that point in time_, other people copied it (starting with your broking firm), and as that strategy became more common your ability to make money disappeared.

I work in the industry, this happens all the time. Trading strategies have a shorter half life than you may think.

Re:How I made $500k with machine learning and high frequency... by Juuumanji on Tuesday November 06, 2012 @11:11AM (#4748997)
that would require some proof that it works today.
Re:How I made $500k with machine learning and high frequency... by beagle3 on Tuesday November 06, 2012 @11:18AM (#4749036)
Not really.

A lot of people in the business would pay e.g. $5,000 for exclusive rights for something that worked this well in 2009 (with proof that it worked in 2009, e.g. verifiable broker statements), and a smaller amount (say, $5,00) for non exclusive rights.

If he claimed it still works but he wants to sell it, it is a completely different game -- because when these things work, they are cash cows.

Re:How I made $500k with machine learning and high frequency... by jspaulding on Tuesday November 06, 2012 @11:55AM (#4749256)
Yes i'm pretty sure it wouldn't work today. By buying the code I realistically mean hiring me to work for them based on what I achieved.
Re:How I made $500k with machine learning and high frequency... by beagle3 on Tuesday November 06, 2012 @03:49PM (#4750664)
The guys you want to work for (2sigma, RenTec, Jane Street, Susquehanna, ...) are unlikely to call you up as a result of this blog post / hacker news exposure/discussion.

If you want to go back to trading, you'll probably have to actively try to get a job -- at the very least, let someone who's still in the business know that you are looking. In my experience in this field, word of mouth and friends-of-friends are infinitely more successful hiring strategies, for both sides.

(Re:releasing the source - I would like to have a look at the strategy, but I would recommend against releasing anything that is even close to being useful, unless you want to spend the next year screening "where can I get a good XTAPI broker" and "I've got XTrader_PRO set up, but I'm getting error 10013, what gives?" emails).

the Nuclear Phynance message board is probably a better place to look for business offers.

Re:How I made $500k with machine learning and high frequency... by Evbn on Tuesday November 06, 2012 @11:24AM (#4749079)
1. Hook

2. Line

3. ...

Profit!