Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Algorithmic Trading: The Play-at-Home Version

wsj.com

Post reply on HN
Print view View original

11–20 of 120 posts

Re: Algorithmic Trading: The Play-at-Home Version

#11

Post by ericjang »

chollida1 wrote: post #9

Here's the problem with trying to create your own trading system. How do you back test it to know that it works. If you back test over the past 5 years then you are only testing your model against a huge bull market. If you back test over the past 20 years then I'm not sure it helps much as the market of 20 years ago didn't really have any of the major market drives of today's markets, HFT's, huge numbers of hedge fu…

One clarification - these mom & pop prop shops aren't necessarily competing against big baskets of MIT PhDs. If your book size is only $200K, the big players (i.e. scores of MIT PhDs) won't even bother competing with you on the same strategies. Alpha from these strategies may very well be orthogonal to hedge fund alpha.

That said, you're still playing a zero sum game with other mom & pop shops and the general large-scale movements of the market. You need to be confident that you have better information / forecasting ability than the others, or technology infrastructure that enables strategies no one else can execute.

Source: I work in the industry.

Re: Algorithmic Trading: The Play-at-Home Version

#12

Post by kittenfluff »

chollida1 wrote: post #9

Here's the problem with trying to create your own trading system. How do you back test it to know that it works. If you back test over the past 5 years then you are only testing your model against a huge bull market. If you back test over the past 20 years then I'm not sure it helps much as the market of 20 years ago didn't really have any of the major market drives of today's markets, HFT's, huge numbers of hedge fu…

> If you back test over the past 5 years then you are only testing your model against a huge bull market.

If your model is long as often as it is short (either cross-sectionally or in a time series sense) then this is less likely to be a problem.

A far bigger source of error for inexperienced researchers is incorrectly accounting (or not accounting at all) for trading costs, financing costs, roll costs, liquidity constraints, data delays, market impact etc.

Re: Algorithmic Trading: The Play-at-Home Version

#13

Post by icefox »

tdees40 wrote: post #3

Whenever people tell me they're going to go into day trading, I usually say, "How many people do you know who've become wealthy day trading?" They say, "Zero." I also know zero people who got rich doing at-home algorithmic trading. But hey, there are probably some! That's the nature of randomness.

I do know at least one person that day traded for a few years. He didn't get rich, but it was in the very nice salary range. Ultimately quit because it was stressful every morning starting all over.

This is also the same reason I only buy undervalued stocks that I hold for years. When I get to the age where I could retire I don't want to have to play the market every morning, I want to do other thing.

Re: Algorithmic Trading: The Play-at-Home Version

#15

Post by des429 »

tdees40 wrote: post #3

Whenever people tell me they're going to go into day trading, I usually say, "How many people do you know who've become wealthy day trading?" They say, "Zero." I also know zero people who got rich doing at-home algorithmic trading. But hey, there are probably some! That's the nature of randomness.

This seems like nonsense to me. How many Phd's are awarded every year? Doesnt mean its a random occurrence... I know quite a few independent day traders who do quite well. I think its about who you know-- i.e if you are working in Finance you'll know more day traders.

Re: Algorithmic Trading: The Play-at-Home Version

#16

Post by jsprogrammer »

chollida1 wrote: post #9

Here's the problem with trying to create your own trading system. How do you back test it to know that it works. If you back test over the past 5 years then you are only testing your model against a huge bull market. If you back test over the past 20 years then I'm not sure it helps much as the market of 20 years ago didn't really have any of the major market drives of today's markets, HFT's, huge numbers of hedge fu…

>How do you back test it to know that it works. If you back test over the past 5 years then you are only testing your model against a huge bull market.

>If you back test over the past 20 years then I'm not sure it helps much as the market of 20 years ago didn't really have any of the major market drives of today's markets, HFT's, huge numbers of hedge funds and the money they bring, and huge passive investing via ETF's, all those factors were there 20 years ago, but they weren't the major market drivers that they are now.

I imagine you wouldn't want to 'back test' over some arbitrarily selected number of years of data. You'd want an adaptive algorithm that could exploit 'trends' over any time period.

But, like someone else mentioned, backtesting is near meaningless: the only thing that matters is actual performance.

Re: Algorithmic Trading: The Play-at-Home Version

#18

Post by jsprogrammer »

des429 wrote: post #15
tdees40 wrote: post #3

Whenever people tell me they're going to go into day trading, I usually say, "How many people do you know who've become wealthy day trading?" They say, "Zero." I also know zero people who got rich doing at-home algorithmic trading. But hey, there are probably some! That's the nature of randomness.

This seems like nonsense to me. How many Phd's are awarded every year? Doesnt mean its a random occurrence... I know quite a few independent day traders who do quite well. I think its about who you know-- i.e if you are working in Finance you'll know more day traders.

Have you seen their trade logs?

Re: Algorithmic Trading: The Play-at-Home Version

#19

Post by baddox »

chollida1 wrote: post #9

Here's the problem with trying to create your own trading system. How do you back test it to know that it works. If you back test over the past 5 years then you are only testing your model against a huge bull market. If you back test over the past 20 years then I'm not sure it helps much as the market of 20 years ago didn't really have any of the major market drives of today's markets, HFT's, huge numbers of hedge fu…

You could say the same thing about starting a business, or choosing a college degree, or taking a certain job.

Re: Algorithmic Trading: The Play-at-Home Version

#20

Post by namecast »

chollida1 wrote: post #9

Here's the problem with trying to create your own trading system. How do you back test it to know that it works. If you back test over the past 5 years then you are only testing your model against a huge bull market. If you back test over the past 20 years then I'm not sure it helps much as the market of 20 years ago didn't really have any of the major market drives of today's markets, HFT's, huge numbers of hedge fu…

> If you back test over the past 20 years then I'm not sure it helps much as the market of 20 years ago didn't really have any of the major market drives of today's markets

+1, and I'll add a link that argues that data pre-2009 is worthless for a great many (intraday) strategies:

http://www.priceactionlab.com/Blog/2015/07/historical-data-t...

And this is before we even start worrying about in-sample vs. out-of-sample...!

Post reply on HN