Just a word of caution: the profitability of stock trading, regardless of the timeframe (high-frequency, daytrade, week long positions), heavily depends on access to information. So even if you build a system that mathematically is better than those built by a team of physicists at large financial institutions, it may easily under-perform the market due to its limited access to data.
Ask HN: Automate Stock Trading?
11–20 of 77 posts
Re: Ask HN: Automate Stock Trading?
#12This old HN thread may be relevant: https://news.ycombinator.com/item?id=4748624
Re: Ask HN: Automate Stock Trading?
#13Great work! I haven't done such things, but I'm curious: what books/papers is your software based on?
I haven't based this off of any existing papers yet, I'm intending for it to start off as fresh research, and depending on how it goes, maybe include/test theories from existing papers. Do you have any papers that you would recommend?
Re: Ask HN: Automate Stock Trading?
#14This old HN thread may be relevant: https://news.ycombinator.com/item?id=4748624
Thanks for sharing, seems very close to what I'm trying to do. Will give that a thorough read!
Re: Ask HN: Automate Stock Trading?
#15"A mathematician plays the stockmarket" is an interesting read of a smart person who made a bunch of mistakes and lost money. http://www.amazon.com/gp/aw/d/0465054811/ref=mp_s_a_1_sc_1?q...
I haven't read the book. From the description on Amazon it seems the investor/mathematician let his emotions come in the way of his investment decisions which led to him losing money. I think that's a risk we run by providing that human touch, which sometimes may even help us if the software is making stupid decisions. My goal is to build a fully-automated system (no human interference) that makes "confident" decisio…
Your emotional response is telling you that your algorithms won't be affected by emotion. Your emotional response has already caused you to prefer one course of action (algorithms) over another (humans picking stocks).
Good luck though! It sounds interesting!
Re: Ask HN: Automate Stock Trading?
#16If I could just give you one piece of advice it would be this: don't do this. A bit longer: You're a pig headed for the slaughterhouse. Please do it 'for play money' only for the first 5 years or so, if your method makes money over that period then set yourself a goal and if you reach it stop .
If you could please shed some light as to why you hold that opinion (past experience etc.), it would be of great help!
Beating a stock market index is a zero-sum game, and the large players in this market have hundreds of millions of dollars and huge manpower invested in making money of small players like OP. I suppose it's possible in principle to be smarter than them, but that's the bar.
Re: Ask HN: Automate Stock Trading?
#17"A mathematician plays the stockmarket" is an interesting read of a smart person who made a bunch of mistakes and lost money. http://www.amazon.com/gp/aw/d/0465054811/ref=mp_s_a_1_sc_1?q...
I haven't read the book. From the description on Amazon it seems the investor/mathematician let his emotions come in the way of his investment decisions which led to him losing money. I think that's a risk we run by providing that human touch, which sometimes may even help us if the software is making stupid decisions. My goal is to build a fully-automated system (no human interference) that makes "confident" decisio…
Your automated system will require human input. I lost a bunch of money in Jan - I saw a huge drawdown, discovered a fixable flaw in my strategy, panicked and closed my positions. Human inputtime - do I close positions and shut down?
Had I stuck with the flawed strategy, I'd have made (a small amount of) money.
Dont think that you dont need to manage your psychology simply because you are running an algorithm.
Re: Ask HN: Automate Stock Trading?
#18"A mathematician plays the stockmarket" is an interesting read of a smart person who made a bunch of mistakes and lost money. http://www.amazon.com/gp/aw/d/0465054811/ref=mp_s_a_1_sc_1?q...
I haven't read the book. From the description on Amazon it seems the investor/mathematician let his emotions come in the way of his investment decisions which led to him losing money. I think that's a risk we run by providing that human touch, which sometimes may even help us if the software is making stupid decisions. My goal is to build a fully-automated system (no human interference) that makes "confident" decisio…
The problem that we had was "CEO ate babies".
You still have to monitor and read the news , because in our case event if event drivent some things can happen that will negate your result.
Exemple : Elon musk talk too much before a financial report, or feud beetween china governement and Ali Baba.
We still have to monitor the news for this kind of probleme. Even if you automize everything you can't prevent this kind of things. And if you do event driven , you will have to think about this.
Regards
Re: Ask HN: Automate Stock Trading?
#19You may want to take a look at http://quantopian.com/ , who make an engine that does just that. A lot of brokers actually support this. The reason appears to be that there are lots of stock trading packages that people want to use (and to be fair, most brokers' interfaces suck somewhat. Also one interface for 2-3 brokers sounds appealing to me). Here is an article about one such trading API: http://www.quantstart.com…
I had actually looked into quantopian when I was getting started, but decided not to use that for my primary source of backtesting because they place limitations on users since that reduces pressure on their systems, allowing them to scale. This restricts backtesting ability and was a dealbreaker for me. The publicly shared algorithms, on the other hand, seem like they can provide a lot of insight, and I will look into those. Thanks!
Re: Ask HN: Automate Stock Trading?
#20If I could just give you one piece of advice it would be this: don't do this. A bit longer: You're a pig headed for the slaughterhouse. Please do it 'for play money' only for the first 5 years or so, if your method makes money over that period then set yourself a goal and if you reach it stop .
If you could please shed some light as to why you hold that opinion (past experience etc.), it would be of great help!
I'd like to caution that judging from the comments I see from you so far in this, it appears that you have not much knowledge in the area. As such, if you're doing this for fun and learning, great. I'm sure you'll learn a lot. But if you're doing this for money, know that you are playing a difficult game against a lot of very good players.
I once attended a predator-prey algorithm seminar on stock trading at the International Conference on Machine Learning. I came away realizing that a ton of people are in this area, and not just the big banks. If you're doing this, go in realizing that you're trying to ride a bike for the first time without training wheels in a race against experienced motorcyclists.
These will be very good for you:
https://news.ycombinator.com/item?id=8994701
https://news.ycombinator.com/item?id=4360742
edit: spelling