Modeling Dynamic User Interests: A Neural Matrix Factorization Approach

We propose an interpretable model that combines the simplicity of matrix factorization with the flexibility of neural networks to model evolving user interests by efficiently extracting nonlinear patterns from massive text data collections.

• 저널Marketing Science
• 토픽Recommender Systems and Techniques · Information Systems
• DOI10.1287/mksc.2021.1293
• 저자Paramveer S. Dhillon, Sinan Aral