I've typed and deleted this post a few times trying to find a way that it doesn't sound kind of pompous but if it helps save one person alot of money then screw it, I'll sound pompous....
I get asked quite a bit on how to start doing algorithmic trading and the first thing I always tell people is don't.
I think I've said this many times now but the number of people who come at it with the thinking "I'm a computer scientist. I'll just fire up R or python and apply some machine learning to the markets and watch the money roll in" is staggering.
I mean each day 100's of Phd's start with clean market data, more data sources than you could possibly think of and statistical back testing systems that have 1000's of man hours put into them, trying to find a way to make money.
After all of that if you really want to I wrote this in response to an Ask Hacker News a little while ago
https://news.ycombinator.com/item?id=11352562
TL/DR
- focus on time periods greater than a day
- expect to lose money
- expect to take a year to figure out some edge in the market
- most decent trading strategies that a normal person can use come from economic/market insights first and technology second.
The site: https://www.quantstart.com/ is also decent at bringing you up to speed on the math you'll need to know though I believe that the material there oversells how easy it is to find a decent trading strategy.
I get asked quite a bit on how to start doing algorithmic trading and the first thing I always tell people is don't.
I think I've said this many times now but the number of people who come at it with the thinking "I'm a computer scientist. I'll just fire up R or python and apply some machine learning to the markets and watch the money roll in" is staggering.
I mean each day 100's of Phd's start with clean market data, more data sources than you could possibly think of and statistical back testing systems that have 1000's of man hours put into them, trying to find a way to make money.
After all of that if you really want to I wrote this in response to an Ask Hacker News a little while ago
https://news.ycombinator.com/item?id=11352562
TL/DR - focus on time periods greater than a day
- expect to lose money
- expect to take a year to figure out some edge in the market
- most decent trading strategies that a normal person can use come from economic/market insights first and technology second.
The site: https://www.quantstart.com/ is also decent at bringing you up to speed on the math you'll need to know though I believe that the material there oversells how easy it is to find a decent trading strategy.