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

Using Reinforcement Learning in the Algorithmic Trading Problem

arxiv.org

Post reply on HN
Print view View original

61–70 of 139 posts

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#61

Post by amiga_500 »

idohft wrote: post #54
amiga_500 wrote: post #27

Earlier quoted context omitted.

I knew someone would come in with "liquidity". Many HFT jump out when things get volatile, when liquidity is actually required. Ultimately HFT is doing nothing of societal value, the race down to zero is never-ending and we are wasting huge amounts of resources on a totally pointless march towards zero. Exchanges should introduce random delays to allow market participants who really want to hedge / buy / sell, then w…

You were replied to, but I'm going to ask some questions of this moralizing. > Many HFT jump out when things get volatile, when liquidity is actually required. This feels almost like a "no true Scotsman" situation. Why is liquidity not "actually required" when volatility is low? Is it a moral obligation for any trader to catch a falling knife? I see this condition of "when liquidity is actually required", but I never…

> Do you know how efficient the system was before HFT started up? And, do you know how many people were working in trading before, and how many are, for a similar fraction of stock volume?

Again this weirdly mixes HFT with electronic automated trading, which I really don't think anyone in the domain would readily mix.

HFT by arbing over latency is entirely different to the automation of boring trader tasks that see less people employed to do the same thing in the front office.

I can't continue this more, it's just blind allegiance from people who are clearly not in the domain.

HFT != electronic trading

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#62

Post by starpilot »

This is just fitting on noise. The vast majority of movements are random and no more predictable than a coin flip. Before training, your job is to extract that extremely weak signal, then train.

Try generating a time series in Excel with Brownian noise, watch as it is indistinguishable from price charts.

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#63

Post by idohft »

amiga_500 wrote: post #61
idohft wrote: post #54

Earlier quoted context omitted.

You were replied to, but I'm going to ask some questions of this moralizing. > Many HFT jump out when things get volatile, when liquidity is actually required. This feels almost like a "no true Scotsman" situation. Why is liquidity not "actually required" when volatility is low? Is it a moral obligation for any trader to catch a falling knife? I see this condition of "when liquidity is actually required", but I never…

> Do you know how efficient the system was before HFT started up? And, do you know how many people were working in trading before, and how many are, for a similar fraction of stock volume? Again this weirdly mixes HFT with electronic automated trading, which I really don't think anyone in the domain would readily mix. HFT by arbing over latency is entirely different to the automation of boring trader tasks that see l…

I have to disagree, I know that HFT != electronic trading.

HFT is also not equivalent to arbing over latency.

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#65

Post by young_rutabaga »

astrofinch wrote: post #59
young_rutabaga wrote: post #44

Earlier quoted context omitted.

This paper is a hilarious dump of WQ's randomly generated formulas that (hopefully) happen to pass in-sample test. Alpha#33: rank((-1 * ((1 - (open / close))^1))) This formula trivially reduces to rank(open/close - 1) which is an example of a mean-reversion strategy. But: 1) nobody bothered to simplify this formula, 2) as any mean reversion, it is extremely difficult to trade.

Why is mean reversion difficult to trade?

High turnover, high costs. You flip your position too often

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#66

Post by phobar »

nycdatasci wrote: post #57

All profitable automated trading strategies that I'm aware of target a specific inefficiency in the market. What is the inefficiency here? If you can't articulate the inefficiency, it's probably best not to employ the strategy.

Interesting, could you describe one inefficiency that was exploited in the past? I could imagine buying/selling due to spreads between exchanges but is there another not as obvious example?

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#67

Post by auntienomen »

amiga_500 wrote: post #60
twic wrote: post #50

Earlier quoted context omitted.

> If you look the preliminary Q1 results of Virtu Financial [0] (only publicly traded HFT) they seem to be doing more trading than ever in these volatile markets. Similar story from Flow Traders: https://www.flowtraders.com/sites/flow-traders/files/quarter...

Everyone is, volumes are hugely up. The point about liquidity is during the sudden market shifts, not over a quarter!

Perhaps you don't follow the news? This was a quarter rich in sudden market shifts.

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#68

Post by p1esk »

traK6Dcm wrote: post #48
smdz wrote: post #46

Earlier quoted context omitted.

> In addition to that, people who are actually "good" at trading don't publish papers, they silently make money. Well, that is mostly true. But never discount anything. There are people like me who used to love the data analysis and prediction part in these markets. I got hooked to the markets because of it. I was not interested in making money and naively thought my average pay was good enough. When I first built (o…

You make a good point. I've also gotten into trading because I enjoy the algorithmic and mathematical aspects, and I would love to share more of what has been working for me and write extensively about it. And there are probably more people like that out there. However, trading has such a bad reputation and uncertain future that I am not sure that's a good career move. I'm torn. You're right that there are probably s…

So how should we evaluate the quality of a paper on trading AI? I mean the authors might not have access to real data, but their ideas might still be good.

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#69

Post by amiga_500 »

auntienomen wrote: post #67
amiga_500 wrote: post #60

Earlier quoted context omitted.

Everyone is, volumes are hugely up. The point about liquidity is during the sudden market shifts, not over a quarter!

Perhaps you don't follow the news? This was a quarter rich in sudden market shifts.

Thanks, I do follow the news. If you read the threads above again you will see that both posters are fully aware of elevated volume, and the distinction was between HFT melting away during short periods of vol and wider "liquidity" from HFT.

So what seemed like a quick drive by wasn't actually correct.

Re: Using Reinforcement Learning in the Algorithmic Trading Problem

#70

Post by mattkrause »

amiga_500 wrote: post #11
jawns wrote: post #5

Earlier quoted context omitted.

> people who are actually "good" at trading don't publish papers, they silently make money I've long understood that this was true. It makes intuitive sense. But are there any cases where it is not true? Is it possible to "spread the wealth" when it comes to trading, or any money-making endeavor? Or does it always reduce down to "I win only because you lose"?

> Or does it always reduce down to "I win only because you lose"? It is a zero sum game. Nobody is producing anything, therefore for one to win another must lose.

Is that always true?

Melon Usk (say) wants to make cars, but he can’t pay for the factory himself, so he forms a company, sells shares in it, and uses the proceeds to build a factory. Now he and his shareholders can make cars, so the shares are worth more.

Who lost money?

Post reply on HN