10.57647/ijm2c.2026.1602.11

Deep Reinforcement Learning-based Fusion of GRU and NCF for personalized Recommendations

PDF
  • Mahshid Salehi1,
  • Hassan Shakeri*1,
  • Seyyed Javad Seyyed Mahdavi Chabok2,
  1. Department of Computer Engineering, Ma.C, Islamic Azad University, Mashhad, Iran
  2. Department of Electrical Engineering, Ma.C, Islamic Azad University, Mashhad, Iran

Received: 29-07-2025

Revised: 13-10-2025

Accepted: 13-11-2025

Published in Issue 30-06-2026

Published Online: 18-11-2025

Copyright (c) 2025 Mahshid Salehi, Hassan Shakeri, Seyyed Javad Seyyed Mahdavi Chabok (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Salehi, M., Shakeri, H., & Seyyed Mahdavi Chabok, S. J. (2026). Deep Reinforcement Learning-based Fusion of GRU and NCF for personalized Recommendations. International Journal of Mathematical Modelling & Computations, 16(2). https://doi.org/10.57647/ijm2c.2026.1602.11
Crossref
Scopus
Google Scholar
Europe PMC

Abstract

Recommender systems are widely used to deliver efficient, customized content and services, making them effective solutions for managing information overload. Over the past decade, e-commerce apps, including movie apps, have researched and implemented many recommendation algorithms. However, data sparsity is a significant challenge for many movie recommender datasets. This paper introduces a hybrid recommender system that combines temporal data, user clustering, and item features with user-item ratings to enhance recommendation evaluation metrics while reducing the effects of data sparsity. The Gated Recurrent Unit (GRU) model uses user-item ratings and timestamps to predict temporal behavior patterns. NCF makes the second initial prediction using user-item ratings and user clusters. In the third initial prediction, NCF uses movie genres and user-item ratings. The final recommendation score is the weighted average of three model outputs. To optimize the fusion of these outputs for improved prediction, four deep reinforcement learning algorithms, deep Q-learning, Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Proximal Policy Optimization (PPO), are employed. These agents dynamically learn the weights for the fusion process. The experiments utilize MovieLens 100K and 1M datasets. The proposed approach's recommendation quality improvement is measured by precision, recall, MAE, and RMSE.

PDF

References

  1. Hu Z, Cai SM, Wang J, Zhou T. Collaborative recommendation model based on multi-modal multi-view attention network: Movie and literature cases. Applied Soft Computing. 2023; 144: 110518.
  2. Kumar S, De K, Roy PP. Movie recommendation system using sentiment analysis from microblogging data. IEEE Transactions on Computational Social Systems. 2020; (4): 15–23.
  3. Bandreddy S, Ezeife CI, Gidado A. Mining historical multibehavior sequential patterns for e-commerce recommendation. In: Delir Haghighi P, Greguš M, Kotsis G, Khalil I, editors. Information Integration and Web Intelligence. Cham: Springer Nature; 2025. p. 55–74.
  4. Xu K, Zhou H, Zheng H, Zhu M, Xin Q. Intelligent classification and personalized recommendation of e-commerce products based on machine learning. arXiv. 2024; arXiv: 2403. 19345.
  5. Islek I, Oguducu SG. A hierarchical recommendation system for Ecommerce using online user reviews. Electronic Commerce Research and Applications. 2022; 52: 101131.
  6. La Gatta V, Moscato V, Pennone M, Postiglione M, Sperlí G. Music recommendation via hypergraph embedding. IEEE Transactions on Neural Networks and Learning Systems. 2022; 34(10): 7887–99.
  7. Singh J, Sajid M, Yadav CS, Singh SS, Saini M. A novel deep neural-based music recommendation method considering user and song data. In: 2022 6th International Conference on Trends in Electronics and Informatics (ICOEI). IEEE; 2022. p. 1–7.
  8. Lyu Y, Yin H, Liu J, Liu M, Liu H, Deng S. Reliable recommendation with review-level explanations. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE; 2021. p. 1548–58.
  9. Zheng T, et al. Revisiting review helpfulness prediction: An advanced deep learning model with multimodal input from Yelp. International Journal of Hospitality Management. 2023;114:103579.
  10. G K, K MR, Haldar A. Job recommendation system using LinkedIn user profiles. In: 2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE). 2024. p. 1–6. doi: https://doi.org/10.1109/icETITE58242.2024.10493325
  11. Alsaif SA, Sassi Hidri M, Eleraky HA, Ferjani I, Amami R. Learning based matched representation system for job recommendation. Computers. 2022; 11(11): 161.
  12. Nilashi M, Ibrahim O, Ithnin N. Hybrid recommendation approaches for multi-criteria collaborative filtering. Expert Systems with Applications. 2014; 41(8): 3879–90.
  13. Valcarce D, Landin A, Parapar J, Barreiro Á. Collaborative filtering embeddings for memory-based recommender systems. Engineering Applications of Artificial Intelligence. 2019; 85: 347–56.
  14. Islam MZ, Liu J, Liu L, Li J, Kang W. Semantic explanations in ensemble learning. In: Advances in Knowledge Discovery and Data Mining. PAKDD 2019. Springer; 2019. p. 29–41.
  15. Çano E, Morisio M. Hybrid recommender systems: A systematic literature review. Intelligent Data Analysis. 2017; 21(6): 1487–1524. doi: https://doi.org/10.3233/IDA-163209
  16. Li G, Zhang J. Music personalized recommendation system based on improved KNN algorithm. In: 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC). IEEE; 2018. p. 777–81.
  17. Singh RH, Maurya S, Tripathi T, Narula T, Srivastav G. Movie recommendation system using cosine similarity and KNN. International Journal of Engineering and Advanced Technology. 2020; 9(5): 556–9.
  18. Xu C. A novel recommendation method based on social network using matrix factorization technique. Information Processing & Management. 2018; 54(3): 463–74.
  19. Liu N, Zhao J. Recommendation system based on deep sentiment analysis and matrix factorization. IEEE Access. 2023; 11: 16994–17001.
  20. Anijri SN, Ding D, Song Y, Sun Y. A multiplex hypergraph attribute-based graph collaborative filtering for cold start POI recommendation. IEEE Transactions on Big Data. 2025.
  21. Zhou W, Tian Y, Haq AU, Ahmad S. An autoencoder based recommendation framework toward cold start problem. The Journal of Supercomputing. 2024; 81(1):234. doi: https://doi.org/10.1007/s11227-024-06721-6
  22. Li F, Qu H, Zhang L, Fu M, Chen W, Yi Z. Q-ADER: An Effective Q-Learning for Recommendation With Diminishing Action Space. IEEE Transactions on Neural Networks and Learning Systems. 2024.
  23. Yun Y, Dai H, An R, Zhang Y, Shang X. Doubly constrained offline reinforcement learning for learning path recommendation. Knowledge-Based Systems. 2024; 284: 111242.
  24. Zhou H, Wang H, Yu Z, Bin G, Xiao M, Wu J. Federated distributed deep reinforcement learning for recommendationenabled edge caching. IEEE Transactions on Services Computing. 2024.
  25. Li Y, Tong X. Trust Recommended Algorithm Based on DDPG and Attention Mechanism. In: 2022 Global Conference on Robotics, Artificial Intelligence and Information Technology (GCRAIT). IEEE; 2022. p. 136-140.
  26. Iftikhar A, Ghazanfar MA, Ayub M, Alahmari SA, Qazi N, Wall J. A reinforcement learning recommender system using biclustering and Markov Decision Process. Expert Systems with Applications. 2024; 237: 121541.
  27. Zhao Y, et al. Multi-scenario combination based on multi-agent reinforcement learning to optimize the advertising recommendation system. In: 2024 5th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA), 2024; p. 190-194. IEEE.
  28. Siet S, Peng S, Ilkhomjon S, Kang M, Park D-S. Enhancing sequence movie recommendation system using deep learning and kmeans. Applied Sciences. 2024; 14(6): 2505.
  29. Saifudin I, Widiyaningtyas T, Zaeni IAE, Aminuddin A. SVDGoRank: Recommender system algorithm using SVD and Gower’s ranking. IEEE Access. 2025.
  30. Hu J, An T, Yu Z, Du J, Luo Y. Contrastive Learning for Cold Start Recommendation with Adaptive Feature Fusion. In: 2025 5th International Conference on Consumer Electronics and Computer Engineering (ICCECE); p. 520-524. IEEE.
  31. Ni J, Cai Y, Tang G, Xie Y. Collaborative filtering recommendation algorithm based on TF-IDF and user characteristics. Applied Sciences. 2021; 11(20): 9554.
  32. Ayub M, et al. Modeling user rating preference behavior to improve the performance of the collaborative filtering based recommender systems. PLoS One. 2019; 14(8): e0220129.
  33. Li Y, et al. Personalized Federated Recommendation for ColdStart Users via Adaptive Knowledge Fusion. In: Proceedings of the ACM on Web Conference 2025; p. 2700-2709.
  34. Alsekait DM, Shdefat AY, Mostafa N, Hamdy AMM, Fathi H, AbdElminaam DS. Next-generation movie recommenders: leveraging hybrid deep learning for enhanced personalization. Applied Mathematics. 2024; 18(5): 957-981.
  35. Lee S, Ahn J, Kim N. Embedding enhancement method for LightGCN in recommendation information systems. Electronics. 2024; 13(12): 2282.
  36. Reddy MS, Karnati H, Sundari LM. Transformer based federated learning models for recommendation systems. IEEE Access. 2024.
  37. Mu Y, Wu Y. Multimodal movie recommendation system using deep learning. Mathematics. 2023; 11(4): 895.
  38. Harper FM, Konstan JA. The movielens datasets: History and context. ACM Transactions on Interactive Intelligent Systems (TIIS). 2015; 5(4): 1-19.
  39. Zhang J, Wang Y, Yuan Z, Jin Q. Personalized real-time movie recommendation system: Practical prototype and evaluation. Tsinghua Science and Technology. 2020; 25(2): 180-191. doi: https://doi.org/10.26599/TST.2018.9010118