Predict your Click-out: Modeling User-Item Interactions and Session Actions in an Ensemble Learning Fashion
This work addresses session-based recommendation for e-commerce or content platforms, but it is incremental as it combines existing methods without introducing a fundamentally new approach.
The paper tackled the task of predicting the last click-out in session-based interactions for the RecSys Challenge 2019, achieving a Mean Reciprocal Rank of 0.60277 on the local test set using an ensemble of matrix factorization and a recurrent neural network.
This paper describes the solution of the POLINKS team to the RecSys Challenge 2019 that focuses on the task of predicting the last click-out in a session-based interaction. We propose an ensemble approach comprising a matrix factorization for modeling the interaction user-item, and a session-aware learning model implemented with a recurrent neural network. This method appears to be effective in predicting the last click-out scoring a 0.60277 of Mean Reciprocal Rank on the local test set.