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

A web-reading bot made millions on the options market

slate.com

Post reply on HN
Print view View original

41–50 of 134 posts

Re: A web-reading bot made millions on the options market

#41

Post by x0054 »

downandout wrote: post #12

"The trade occurred 19 seconds before the tweet, and one second after a headline appeared on the Dow Jones Newswire." I don't understand the mystery here. It would be trivial to write a bot that could interpret a headline and make a trade on it in under a second, and that's without any special high-speed links. With API documentation for a brokerage house, I could write such a bot in probably half a day. Given the as…

Automatic trading is an automatic occurrence in deed, and many bots are design to respond to news, tweets, and all kinds of things. That said, if you really think you can write a bot that can do really good in the market, why not just make one. For the sake of argument, just assume that you can confirm a trade in 1-5 seconds, make a bot that just does fake trades, give it $10k in fake currency, and let it play.

Come to think about it, such a system, with an API, would be really nice to have. Something that allows anyone to create a trading bot and see how it performs. Any one what to make one? :)

Re: A web-reading bot made millions on the options market

#42

Post by def_illiterate »

x0054 wrote: post #41
downandout wrote: post #12

"The trade occurred 19 seconds before the tweet, and one second after a headline appeared on the Dow Jones Newswire." I don't understand the mystery here. It would be trivial to write a bot that could interpret a headline and make a trade on it in under a second, and that's without any special high-speed links. With API documentation for a brokerage house, I could write such a bot in probably half a day. Given the as…

Automatic trading is an automatic occurrence in deed, and many bots are design to respond to news, tweets, and all kinds of things. That said, if you really think you can write a bot that can do really good in the market, why not just make one. For the sake of argument, just assume that you can confirm a trade in 1-5 seconds, make a bot that just does fake trades, give it $10k in fake currency, and let it play. Come…

I imagine there would be pretty good money in licensing an API. That's probably where the real money is--let the idiots make the trades, and you sell them the software.

Re: A web-reading bot made millions on the options market

#43

Post by onewaystreet »

xyzzy123 wrote: post #13
downandout wrote: post #12

"The trade occurred 19 seconds before the tweet, and one second after a headline appeared on the Dow Jones Newswire." I don't understand the mystery here. It would be trivial to write a bot that could interpret a headline and make a trade on it in under a second, and that's without any special high-speed links. With API documentation for a brokerage house, I could write such a bot in probably half a day. Given the as…

Probably because you've never bet a lot of money on natural language processing before. Backtest and check alpha. cpercival's idea is pretty good though. I'm reminded of: https://xkcd.com/793/

These bots don't actually do much analysis. They just weight keywords and sources. "Buys" or "acquisition" in a WSJ headline has a pretty clear cut meaning. Financial headlines also tend to be pretty easy to parse (e.g. "X Buys Y").

Re: A web-reading bot made millions on the options market

#44

Post by venomsnake »

WalterBright wrote: post #18
kenrikm wrote: post #17

Next step, make a bot to tweet out (fake) news to trigger this bot and place itself on the winning side of the trade.

That's called "pump and dump", and I believe it is illegal.

They can send the bots to jail.

Re: A web-reading bot made millions on the options market

#45

Post by gnaritas »

x0054 wrote: post #41
downandout wrote: post #12

"The trade occurred 19 seconds before the tweet, and one second after a headline appeared on the Dow Jones Newswire." I don't understand the mystery here. It would be trivial to write a bot that could interpret a headline and make a trade on it in under a second, and that's without any special high-speed links. With API documentation for a brokerage house, I could write such a bot in probably half a day. Given the as…

Automatic trading is an automatic occurrence in deed, and many bots are design to respond to news, tweets, and all kinds of things. That said, if you really think you can write a bot that can do really good in the market, why not just make one. For the sake of argument, just assume that you can confirm a trade in 1-5 seconds, make a bot that just does fake trades, give it $10k in fake currency, and let it play. Come…

Those systems exist, Metatrader, TradeStation, NinjaTrader, and people do exactly that and have been for years.

Re: A web-reading bot made millions on the options market

#46

Post by stevewilhelm »

downandout wrote: post #12

"The trade occurred 19 seconds before the tweet, and one second after a headline appeared on the Dow Jones Newswire." I don't understand the mystery here. It would be trivial to write a bot that could interpret a headline and make a trade on it in under a second, and that's without any special high-speed links. With API documentation for a brokerage house, I could write such a bot in probably half a day. Given the as…

Most financial news feeds are distributed in a standard format. [1]

https://iptc.org/standards/

Re: A web-reading bot made millions on the options market

#47

Post by MichaelCrawford »

I once wrote a special-purpose database kernel - not SQL, the database engine itself - for a Bahamian hedge fund.

It is because of my experience with that hedge fund that I won't take quantitative investment work anymore. I came to regard it as unethical.

I would not be in any way surprised if it were my former clients that pulled this off. There were some smart people there.

Re: A web-reading bot made millions on the options market

#48

Post by lordnacho »

MichaelCrawford wrote: post #47

I once wrote a special-purpose database kernel - not SQL, the database engine itself - for a Bahamian hedge fund. It is because of my experience with that hedge fund that I won't take quantitative investment work anymore. I came to regard it as unethical. I would not be in any way surprised if it were my former clients that pulled this off. There were some smart people there.

What was unethical about it? Quantitative investment work can mean a lot of things.

Re: A web-reading bot made millions on the options market

#49

Post by hueving »

cperciva wrote: post #30
hueving wrote: post #27

Earlier quoted context omitted.

There are many times a news story appears about a company that have absolutely no impact on the stock. In fact, the anticipation of a news story that turns out to be nothing note worthy will lead to a drop in volatility and make your trade a losing one. See every time a company announces earnings in line with expectations for example. "x company made 1 billion in profit" could fail to move the stock at all. Betting t…

Betting that news is market moving requires a decent amount of analysis of the news and the credibility of its source. You don't need to be right every time in order to make a profit in the long run.

You missed the point I was making about news releases causing a drop in volatility when it confirms expectations.

Re: A web-reading bot made millions on the options market

#50

Post by cperciva »

hueving wrote: post #49
cperciva wrote: post #30

Earlier quoted context omitted.

Betting that news is market moving requires a decent amount of analysis of the news and the credibility of its source. You don't need to be right every time in order to make a profit in the long run.

You missed the point I was making about news releases causing a drop in volatility when it confirms expectations.

As long as news releases usually increase volatility, you're fine.
Post reply on HN