noob question - best way to detect if news is affecting a stock?

Hi Guys,

First post so go easy please ;-)

I'm an experienced software developer with some time on my hands now and I'm looking to create a free system that will detect stock movements and then check pretty much every news source that can be checked online for news regarding this company. So that's blogs, social media, news websites etc. With the aim of getting this information to the user as quickly as possible.

At the moment I'm not sure whats the best way to detect that something might be effecting a stock, I was going to go with just the price of the stock but then I thought some news may be interpreted as good to some and bad to others so the price might not actually change much. Then I thought of checking the volume of the stock over a short interval. I saw some websites do offer this but it appears they don't show "out of hours" trading volume. Is that correct? If not can someone point me in the direction of one that does?

What stats would you guys recommend looking at to detect "interest/purchases" and where is the best place to source these stats/figures?

Any help at all would be greatly appreciated :-)

Thanks!
 
I'm an experienced software developer with some time on my hands now and I'm looking to create a free system that will detect stock movements and then check pretty much every news source that can be checked online for news regarding this company. So that's blogs, social media, news websites etc. With the aim of getting this information to the user as quickly as possible.


Two things straight off the bat:

(a) Its been done before. I would strongly suggest you thoroughly research what your "competitors" are up to before expending your energy. As a one-man coder with some time on your hands, you need to be sure you have something unique to offer a crowded marketplace !

(b) If you're not planning to pay for data or news feeds, then I would say forget the idea. Basing your project on screen-scraping is, at best going to yield mediocre results with lots of false-positives/false-negatives .... and at worst, going to drive you crazy adapting your code for all sorts of edge-cases because you're not building it off APIs.

Finally, if I may, I real-life true story.....

Once upon a time, I had a decent chunk of shares in a large-ish midcap.

One day, mid-morning, the shares started falling off a cliff.

By lunch time they were down something like 15%, and still plummeting like lemmings.

Now, my Google-fu is pretty good, and I also had access to a few paid news-feeds of reasonable quality. But I'd spent the morning trying to figure out what was going on and all my searches were coming up empty-handed (and yes that includes checking Twitter & co.)

Eventually.... at 13:20 (!!), something appeared on a friend's Bloomberg screen. A news article referencing a couple of phrases hidden in a page-long news article, written elsewhere, in German and hosted on an obscure Swiss news website.

Once it had appeared on the Bloomberg feed, it eventually started trickling through to other paid news feeds (including the ones I'd paid for), and then eventually on to the freebies.

So the moral of the story is, if it took Bloomberg half a day to post something in English, then, well, I think you know what I'm saying, especially if you're not going to be paying for live Bloomberg/Reuters news feeds....

(And no, I wouldn't even think about automated translations. Even stuff like Google Translate with all the money and brains Google throws at it, remains pretty poor compared to what true native speakers can do .... the above story is testament to that, because the friend gave me the original link off Bloomberg and I tried running it through a few auto-translators, they all failed, it was evidently something that needed a human speaker)
 
Last edited:
Two things straight off the bat:

(a) Its been done before. I would strongly suggest you thoroughly research what your "competitors" are up to before expending your energy. As a one-man coder with some time on your hands, you need to be sure you have something unique to offer a crowded marketplace !

(b) If you're not planning to pay for data or news feeds, then I would say forget the idea. Basing your project on screen-scraping is, at best going to yield mediocre results with lots of false-positives/false-negatives .... and at worst, going to drive you crazy adapting your code for all sorts of edge-cases because you're not building it off APIs.

Finally, if I may, I real-life true story.....

Once upon a time, I had a decent chunk of shares in a large-ish midcap.

One day, mid-morning, the shares started falling off a cliff.

By lunch time they were down something like 15%, and still plummeting like lemmings.

Now, my Google-fu is pretty good, and I also had access to a few paid news-feeds of reasonable quality. But I'd spent the morning trying to figure out what was going on and all my searches were coming up empty-handed (and yes that includes checking Twitter & co.)

Eventually.... at 13:20 (!!), something appeared on a friend's Bloomberg screen. A news article referencing a couple of phrases hidden in a page-long news article, written elsewhere, in German and hosted on an obscure Swiss news website.

Once it had appeared on the Bloomberg feed, it eventually started trickling through to other paid news feeds (including the ones I'd paid for), and then eventually on to the freebies.

So the moral of the story is, if it took Bloomberg half a day to post something in English, then, well, I think you know what I'm saying, especially if you're not going to be paying for live Bloomberg/Reuters news feeds....

(And no, I wouldn't even think about automated translations. Even stuff like Google Translate with all the money and brains Google throws at it, remains pretty poor compared to what true native speakers can do .... the above story is testament to that, because the friend gave me the original link off Bloomberg and I tried running it through a few auto-translators, they all failed, it was evidently something that needed a human speaker)

That's a pretty interesting story man. That's the exact the sort of scenario that my software would aim to help its users avoid. That news could of being found easily if an index of finance related websites was crawled for that companies name/board member names every few minutes. Can you remember the website out of curiosity?
 
So the moral of the story is, if it took Bloomberg half a day to post something in English, then, well, I think you know what I'm saying, especially if you're not going to be paying for live Bloomberg/Reuters news feeds....
Thanks for the story. Seen that so much it is not funny - checking every where for an explanation of what is happening and never being able to find it. Even if you want to scrape for news on finance sites like Yahoo Finance, there is so much crap thrown at you, you get tired before getting to the real driver of price moves.
 
Back
Top