I have a StackOverflow question answer dataset. ( this is a classification problem )

So , far I have created two different models.

Model 1: LightGBM model optimized.

Data fed into LightGBM model contains all the feature engineered attributes from the StackOverflow posts and person who had posted questions.

One snapshot of the data is something like this :

feature engineered dataframe

Model 2:

Neural Network-based model in which I am taking only question text and taking its word embeddings.

My question is can combine both of these models using something like StackNet ? If yes how ?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.