Integration of Deep Reinforcement Learning with Collaborative Filtering for Movie Recommendation Systems

Abstract

In the era of big data, effective recommendation systems are essential for providing users with personalized content and reducing search time on online platforms. Traditional collaborative filtering (CF) methods face challenges like data sparsity and the new-user or cold-start issue, primarily due to their reliance on limited user–item interactions. This paper proposes an innovative movie recommendation system that integrates deep reinforcement learning (DRL) with CF, employing the actor–critic method and the Deep Deterministic Policy Gradient (DDPG) algorithm. This integration enhances the system’s ability to navigate the recommendation space effectively, especially for new users with less interaction data. The system utilizes DRL for making initial recommendations to new users and to generate optimal recommendation as more data becomes available. Additionally, singular value decomposition (SVD) is used for matrix factorization in CF, improving the extraction of detailed embeddings that capture the latent features of users and movies. This approach significantly increases recommendation precision and personalization. Our model’s performance is evaluated using the MovieLens dataset with metrics like Precision, Recall, and F1 Score and demonstrates its effectiveness compared with existing recommendation benchmarks, particularly in addressing sparsity and new-user challenges. Several benchmarks of existing recommendation models are selected for the purpose of model comparison.

Enhancing Personalized Recommendations: A Study on the Efficacy of Multi-Task Learning and Feature Integration

“…CF methods, such as matrix completion, remain prevalent due to their effectiveness in capturing user-item interactions [16,17]. They suffer, however, from the cold-start problem and data sparsity issues [18,19]. Content-based filtering, on the other hand, is increasingly leveraging advanced techniques for similarity computations based on user profiles and item metadata [20][21][22], which can help overcome some limitations of CF, but is still dependent on the quality and availability of data [23].…”

“…Total Loss = ω likeability •Likability Loss + ω rating •Rating Loss (18) where ω likeability and ω rating are the weights for the likability prediction and rating estimation tasks, respectively. These weights control the contribution of each task to the overall loss.…”

“…The loss function for the likability prediction task is given by Equation ( 15), while the loss function for the rating estimation task is given by Equation ( 16). The overall loss function was calculated using Equation (18), with the weights ω likeability and ω rating set to 1 by default. The final loss value was 0.0026, where the Likability_Predictor loss was 1.2336 × 10 −4 , and the Rating_Estimator loss was 0.0024.…”