RSAttAE: An Information-Aware Attention-based Autoencoder Recommender System
This work addresses the problem of enhancing customer satisfaction in the entertainment sector through improved recommender systems, which is an incremental solution for an existing challenge.
The authors tackled the problem of predicting unknown user-movie ratings and achieved results that outperform most existing state-of-the-art methods. Their approach demonstrated improved performance on the MovieLens 100K dataset.
Recommender systems play a crucial role in modern life, including information retrieval, the pharmaceutical industry, retail, and entertainment. The entertainment sector, in particular, attracts significant attention and generates substantial profits. This work proposes a new method for predicting unknown user-movie ratings to enhance customer satisfaction. To achieve this, we utilize the MovieLens 100K dataset. Our approach introduces an attention-based autoencoder to create meaningful representations and the XGBoost method for rating predictions. The results demonstrate that our proposal outperforms most of the existing state-of-the-art methods. Availability: github.com/ComputationIASBS/RecommSys