What I want is to identify sets of conditions that are a leading indicator of a stock movement. For example, if my dog hears rattling of keys and sees me putting on my shoes, it’s a sign of the possibility of going on a walk. For experts in the stock market, this is quite duh. However, for everyday people like me (the amateurs), we tend to be more reactive. Meaning, we tend to become attracted to a stock after it starts rising. So, amateurs normally have one leading indicator and that is “a good stock to buy is one that is rising.” It’s rare that amateurs can take advantage of significant moves once it’s actually noticed.
I’m using the association rules algorithm from Analysis Services 2005 to figure out things like: On days that INTC rises significantly, MSFT often rises significantly too. However, I don’t intend to use that knowledge to simply buy MSFT when I notice INTC going up. There’s not much value in that in itself. The value arises in realizing there is a connection between the fortunes of MSFT and INTC. So, if there is a situation where INTC announces its quarterly earnings before MSFT, I’ll have a good clue that MSFT’s quarter will be similar. This won’t work well on stocks as well-known as these two. If INTC announced a great quarter, MSFT will immediately start rising. But perhaps there are pairs that go relatively unnoticed.