Explanations for Temporal Recommendations
This addresses the need for interpretable AI in commercial recommendation systems, but it is incremental as it combines existing LSTM and neighborhood-based methods.
The paper tackles the problem of non-interpretability in deep learning-based recommendation systems by proposing a framework for explainable temporal recommendations, achieving joint optimization for prediction accuracy and explainability on the Netflix dataset.
Recommendation systems are an integral part of Artificial Intelligence (AI) and have become increasingly important in the growing age of commercialization in AI. Deep learning (DL) techniques for recommendation systems (RS) provide powerful latent-feature models for effective recommendation but suffer from the major drawback of being non-interpretable. In this paper we describe a framework for explainable temporal recommendations in a DL model. We consider an LSTM based Recurrent Neural Network (RNN) architecture for recommendation and a neighbourhood-based scheme for generating explanations in the model. We demonstrate the effectiveness of our approach through experiments on the Netflix dataset by jointly optimizing for both prediction accuracy and explainability.