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

71–80 of 120 posts

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

#71

Post by siavosh »

baudehlo wrote: post #67
siavosh wrote: post #23

How is this new? The first time I setup my own linux server was at my parent's house, so I could write a crawler to collect market data in the hopes of applying some AI technique for market predictions. This was 10 years ago. It's a lot of programmers dream to write a little program that can print money. Afterwards I went and worked on wallstreet, and realized how foolish this was.

If you learn something while writing it, and it sits and earns a little bit of money without much work, then it's not really foolish. I bet you learned more doing that project, things that probably helped get you that Wall Street job, than you seem to estimate now.

Sure there's always value in doing. What I believe is foolish after learning more about what the industry does is the belief that a DIY program can actually make money.

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

#72

Post by baudehlo »

siavosh wrote: post #71
baudehlo wrote: post #67

Earlier quoted context omitted.

If you learn something while writing it, and it sits and earns a little bit of money without much work, then it's not really foolish. I bet you learned more doing that project, things that probably helped get you that Wall Street job, than you seem to estimate now.

Sure there's always value in doing. What I believe is foolish after learning more about what the industry does is the belief that a DIY program can actually make money.

You probably can't beat the market. But if you can beat a savings account earning 2% interest it's probably worth it for the learning experience.

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

#73

Post by tomp »

murbard2 wrote: post #54
ericjang wrote: post #11

Earlier quoted context omitted.

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-s…

Yes and no. If it can be automated, no amount is too small to collect. A hobbyist best shot is to do... things that don't scale. Source: I do too.

I'm not sure about that. If a $2bn hedge fund finds 100 different "alpha strategies" for turning $20k into $200k, that's still just 1% to their bottom line. Probably not worth the time.

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

#74

Post by tomp »

jsprogrammer wrote: post #16
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…

> You'd want an adaptive algorithm that could exploit 'trends' over any time period.

Of course that what you want, but how will you find it, and more importantly, how will you know you found it? In a bull market, an "adaptable general algorithm" that makes 10% in a year is statistically indistinguishable from an algorithm that buys and holds S&P500, unless you design your backtests very carefully.

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

#75

Post by murbard2 »

tomp wrote: post #73
murbard2 wrote: post #54

Earlier quoted context omitted.

Yes and no. If it can be automated, no amount is too small to collect. A hobbyist best shot is to do... things that don't scale. Source: I do too.

I'm not sure about that. If a $2bn hedge fund finds 100 different "alpha strategies" for turning $20k into $200k, that's still just 1% to their bottom line. Probably not worth the time.

That's $20,000,000 which is enough to warrant at least 10 people working on it.

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

#76

Post by siavosh »

baudehlo wrote: post #72
siavosh wrote: post #71

Earlier quoted context omitted.

Sure there's always value in doing. What I believe is foolish after learning more about what the industry does is the belief that a DIY program can actually make money.

You probably can't beat the market. But if you can beat a savings account earning 2% interest it's probably worth it for the learning experience.

Well, you'd have to beat 2% + transaction fees + capital gains which would mean you'd have to beat the market.

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

#77

Post by jsprogrammer »

tomp wrote: post #74
jsprogrammer wrote: post #16

Earlier quoted context omitted.

>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…

> You'd want an adaptive algorithm that could exploit 'trends' over any time period. Of course that what you want , but how will you find it, and more importantly, how will you know you found it? In a bull market, an "adaptable general algorithm" that makes 10% in a year is statistically indistinguishable from an algorithm that buys and holds S&P500, unless you design your backtests very carefully.

Obviously it is a problem, but it will get you much further than the original suggestion to select some arbitrary number of days to go back.

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

#78

Post by psykotic »

infinite8s wrote: post #52
ericjang wrote: post #51

Earlier quoted context omitted.

Sorry, it was not my intention to suggest that trading is not productive, or that it's truly a zero-sum game. You probably know this already, but I'll provide some more context for the interested: In reality, two parties can walk away from a trade believing (in the moment) that they got the better deal. Otherwise, they wouldn't be trading in the first place. This results because people have different utility function…

Are there prop shops with books that small?

Lots of them. "Prop shop" can be a glorified term for someone trading out of their personal funds.

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

#80

Post by noname123 »

throwawaymsft wrote: post #68
noname123 wrote: post #26

Interesting article but for a different take on a statistical approach to the market, curious if any peeps on HN are into volatility trading? From what I understand a lot of the "DIY vendors" cater to the equity crowd, meaning people who build their models on technical indicators (MACD, RSI, advancers/decliners ratio, Fibonacci golden ratio retracement, MA); you build your model of some combined signals, back-test it…

I do something similar trading volatility, using mean reversion/contango to make directional options plays. After a spike like Grexit volatility tends to return to its historical mean.

OK. Cool, I assume you trade either VIX put spreads or calendar spreads, or short VXX or long XIV on a VIX spike? If so, I do this as well. :)
Post reply on HN