Is there any good method to merge/consolidation different predictive models which were trained on different features but outputs the same goal.
Example:
Model 1 with features a + b + c (trained on decision tree) = probability of hot/cold
Model 2 with features d + e + f (trained on svm) = probability of hot/cold
Note that : It is not possible to merge a,b,c,d,e,f into one file as they were collected at different time stamps.
Please guide me how to consolidate both models to come up with one result i.e probability of hot/cold
(I have already tried weighted approach where x% weight is assign to model1 & (100-x%) weight assigned to model2), but I would like to utilize much better approach which is statistically correct.
