Hacker News new | past | comments | ask | show | jobs | submit login

You could do some very simple keyword analysis to filter that out, though. When words like "the deal", "in talks to buy", "to acquire", etc. appear, it's a pretty good bet that it has something to do with an acquisition, and also a good bet that volatility will spike.

A lot of people here are saying "I wouldn't bet $2.4M on that false positive rate", but that's not how traders think. You only have to be right more often than you're wrong (or alternatively, very right to offset being wrong a lot more often) - "betting" is exactly what they do for a living. It's pretty much the perfect application for statistical machine learning - users never see how bad your algorithms are, and so it doesn't matter if the quality is worse than a human as long as the speed is better.




"the deal"... Is still being negotiated Company x has been looking "to acquire" a player in field y for some time and hasn't found any candidates yet.

Keyword analysis by itself is almost completely useless.


Since when do newspapers write about the lack of something happening? That's sort of anti-news, isn't it? I could potentially see them writing something like that as a throwaway sentence in another article about the company, but the phrasing you've quoted is incredibly awkward and would probably never make it into a real news story.

Also, an algorithm doesn't have to be perfect, it merely has to be right more often than it's wrong. So what if you get a few false positives and a couple of your trades blow up? That's why you're managing a portfolio and not dumping your entire assets into a single trade.


When it comes to market speculation, non-news is published quite frequently. Often time it comes in the form of stories that summarize what happened that week.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: