Stock Market pattern recognition with machine learning

Greetings,

I've started to study statistics and R studio in general, to utilize it in my stock market trading. I dreamed of a market indicator, that analyzes exported data, via R studio (and perhaps h2o, which I am also studying).
The concept is, that I export csv's for 4 different time frames, and 200 observations of numerous variables in each. For each set of this (labeled) data, I want to tell the system that this is a long entry situation, that is a short entry situation, while others are neutral situations, so I want R studio to return the class of the entered data, peridoically. Is there such model? As far as I know, none of the basic models would fit my needs (neither linear/logistic regression, nearest neighbours, K means, decision trees nor SVMs), since these are classification models, but can only return binary values.
Please advise me, where to head to? Did I miss something?

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.