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

How I made $500k with machine learning and high frequency trading

jspauld.com

Post reply on HN
Print view View original

101–110 of 320 posts

Re: How I made $500k with machine learning and high frequency trading

#101

Post by dschiptsov »

mattyppants wrote: post #91
dschiptsov wrote: post #71

Basically this is a story about a guy who was smart enough to script up his trading tool (he discovered that there is an API and wrote some code to use it). He trade other people's money, using other people's (probably employer's) account and resources, I suppose. His employer have paid all the fees, and, took all the risks - if there is profit - it is mine, if there is a lose - it is theirs.) The essence of trading…

This is not even close to an accurate summary. He never stated that he had any employer backing, and he wasn't collecting market making fees. In fact he was paying brokerage fees which is the exact opposite.

He used his own money to test his algos? Come on.

Taking a Machine Learning and Statistics course does not make you a trader. You need something else - access to the system.

This is why my guess is that he was an employee.

Re: How I made $500k with machine learning and high frequency trading

#102

Post by agilebyte »

motters wrote: post #56
tarr11 wrote: post #23

This is just glorified gambling. I am not sure what special insight or advantage he had, other than his own model. Every trader has a model. It could have easily been called "how i lost 500k with machine learning". Like gambling, it's easy to manipulate statistics to show that you did well in some period of time. I worked for a large investment bank about 10 years ago, writing trading programs for quant traders who w…

Correct. The far more common story is "how I lost $Xk on the stock market". Probably most people with programming/AI skills have tried their luck with the stock picking problem at one time or another. I have a few times, but only in simulation. Even using very elaborate machine learning methods and a lot of training data, making money from automated trades is a difficult problem, and my impression is that it's very m…

How is it like horses and football games? Don't the latter have a lot more people playing with their emotion rather than utilizing an algorithm? Something that you can take advantage of?

Re: How I made $500k with machine learning and high frequency trading

#103

Post by loup-vaillant »

While this was quite fascinating, I couldn't see this form of trading as anything but a zero-sum game. Some players win, the other lose, like in any other game.

Except finance is supposed to be "serious". In most serious, legitimate activities, extracting money means you provided value somehow. So, what value high frequency trading could possibly provide?

Re: How I made $500k with machine learning and high frequency trading

#104

Post by sseveran »

hafabnew wrote: post #89

I've been considering trying HFT myself for a while. I'm competent with Machine Learning and am a Software Developer by day, so I can program and can sysadmin well enough to get something up and running without any trouble at all. But, every time I've tried to actually get started, I've always found the amount of research required before being able to begin is just staggering. It seems like the logical course of sing…

Nothing in HFT is free. People doing this for a living use precision time protocol in a colocated data center to build their own timestamps. However you can get started by buying ITCH, OpenBook, etc... data which has the full market depth feeds for the various exchanges. There are a couple of brokers out there specializing in the space.

If the easy part was building a working model either you got incredibly lucky or the model is wrong.

Re: How I made $500k with machine learning and high frequency trading

#105

Post by jcampbell1 »

S_A_P wrote: post #67
lrm242 wrote: post #28

Take a look at the VIX from 2009 until today and you'll understand why you stopped making money.

http://finance.yahoo.com/echarts?s=%5EVIX+Interactive#symbol... ; very interesting, a spike in sept-dec 2009 that roughly follows his PNL...

Without a ton of volatility, any homebrew HFT is going to lose to commissions and spread. Basically, he was trading in one of the few periods where is was possible to make money.

Re: How I made $500k with machine learning and high frequency trading

#106

Post by arbuge »

jspaulding wrote: post #97
arbuge wrote: post #62

I am curious as to exactly why the profitability decreased steadily and rather rapidly all the way to ~zero. The article doesn't seem to expound on that unless I missed something. Is this a result of bots on the other side adapting in some way to what you were doing? I would have thought you would be too small a player for them to notice.

I don't think anyone was adapting to what I was doing in particular but rather simply adapting to the opportunities in the market.

Thanks. Makes sense... I guess those opportunities tend to get ironed out rather fast then.

Re: How I made $500k with machine learning and high frequency trading

#107

Post by jspaulding »

beagle3 wrote: post #54
Juuumanji wrote: post #45

Earlier quoted context omitted.

that would require some proof that it works today.

Not really. A lot of people in the business would pay e.g. $5,000 for exclusive rights for something that worked this well in 2009 (with proof that it worked in 2009, e.g. verifiable broker statements), and a smaller amount (say, $5,00) for non exclusive rights. If he claimed it still works but he wants to sell it, it is a completely different game -- because when these things work, they are cash cows.

Yes i'm pretty sure it wouldn't work today. By buying the code I realistically mean hiring me to work for them based on what I achieved.

Re: How I made $500k with machine learning and high frequency trading

#108

Post by bjourne »

jspaulding wrote: post #81
yajoe wrote: post #43

Earlier quoted context omitted.

This. I love crazy projects and Show HN's until the cows come home, but this one is dangerous that I must repeat the warning to others. I cannot emphasize how important it is to understand that people who trade using price action ( http://en.wikipedia.org/wiki/Price_action_trading ) are just speculating based on where they expect the price to move. It's no different than people who play Texas Hold'em online and specu…

Hey, I didn't actually intend this to be a course. I do not make any money in the market right now so am certainly not qualified to teach a course on it. And of course, if I was making money in the market I wouldn't have posted this at all. So please everyone remember that. These comments have made me realize it's probably for the best if I do not post the source code. Basically you are competing against armies of PH…

Guess you are familiar with http://en.wikipedia.org/wiki/Survivorship_bias? In 2009, there were probably tonnes of people trying to exploit the market using similar low-tech methods as you. Even if all of them were at best break-even, some of them likely made a lot of money on their unprofitable algorithms by pure chance thanks to the size of the cohort. Those few blogged about it and those who lost money didn't. :) I'm not saying that you just were lucky (please dont take this as criticism) - survival bias is just one of those things that always come to mind when people write about how they broke the market or when some investor is presenting his incredibly smart investment strategy that has netted him millions.

Re: How I made $500k with machine learning and high frequency trading

#109

Post by jspaulding »

briancurtin wrote: post #26
jspaulding wrote: post #21

Earlier quoted context omitted.

Yes, however, I forgot to mention that pretty early on I converted my program to use an API from https://www.tradingtechnologies.com . It's odd, but I can't remember exactly why. I think it was simply because I found a broker who could offer me a lower commission rate and they only supported TT. With regard to posting code yes I may do that. We'll see.

XTAPI, or did you write something to talk to a FIX gateway? (former TT employee)

I'm pretty sure it was XTAPI. Is that the simpler one? I used the simpler one. Whatever the case.. the code that dealt with the API was trivial compared to the rest of my program. So good work!

Re: How I made $500k with machine learning and high frequency trading

#110

Post by sseveran »

hooande wrote: post #96
jcromartie wrote: post #6

Earlier quoted context omitted.

I have one question: Why doesn't every hacker do this to make extra money? Is it within the grasp of anybody who can program to automate trading like this? EDIT: Sounds like it's not really for everybody. You have to own or rent a server with access to direct lines to the exchanges, or else your lag will be such that profiting from HFT is impossible. How much do these cost?

Because it's gambling. Some are better gamblers than others, but no individual can consistently have more ups than downs over a period of years. "I was making a lot of money but now I've stopped" is the same thing as "I was lucky until I wasn't". Making a living by gambling pretty much sucks, which is why most hackers don't do it. (You'd think that something as complex as markets would attract hackers trying to "figu…

You are correct that no individual can. But firms can. And some do. Its not gambling. Its not heading down to the roulette wheel. If someone puts on millions of trades and wins a statistically significant portion of them you would have to say its not gambling. Its trading with a statistical edge.
Post reply on HN