Partially Observable Markov Decision Process for Recommender Systems
This addresses performance degradation in online recommender systems, which is an incremental improvement for the domain.
The paper tackles the Recurrent Deterioration phenomenon in recommender systems, where performance degrades due to reliance on user feedback, and proposes the POMDP-Rec framework, which achieves results comparable to expert-tuned models on public datasets.
We report the "Recurrent Deterioration" (RD) phenomenon observed in online recommender systems. The RD phenomenon is reflected by the trend of performance degradation when the recommendation model is always trained based on users' feedbacks of the previous recommendations. There are several reasons for the recommender systems to encounter the RD phenomenon, including the lack of negative training data and the evolution of users' interests, etc. Motivated to tackle the problems causing the RD phenomenon, we propose the POMDP-Rec framework, which is a neural-optimized Partially Observable Markov Decision Process algorithm for recommender systems. We show that the POMDP-Rec framework effectively uses the accumulated historical data from real-world recommender systems and automatically achieves comparable results with those models fine-tuned exhaustively by domain exports on public datasets.