A Neural Network Based Explainable Recommender System
This addresses the need for explainable recommender systems to enhance user trust and engagement, though it is incremental as it builds on existing neural network approaches.
The paper tackled the problem of generating explanations for recommendations in addition to predicting ratings, proposing an integrated neural network model that achieved lower RMSE than traditional methods and produced convincing explanations for users.
Recommendation system could help the companies to persuade users to visit or consume at a particular place, which was based on many traditional methods such as the set of collaborative filtering algorithms. Most research discusses the model design or feature engineering methods to minimize the root mean square error (RMSE) of rating prediction, but lacks exploring the ways to generate the reasons for recommendations. This paper proposed an integrated neural network based model which integrates rating scores prediction and explainable words generation. Based on the experimental results, this model presented lower RMSE compared with traditional methods, and generate the explanation of recommendation to convince customers to visit the recommended place.