1. MMC
  2. All Volumes and Issues
  3. Volume 12, Number 4, 2025
  4. Exploring LSTM-CAMF: A New Approach for Context-Aware Collaborative Filtering

Exploring LSTM-CAMF: A New Approach for Context-Aware Collaborative Filtering

MMC.
2025;
Volume 12, Number 4
: pp. 1221–1231
Received: May 06, 2025
Revised: November 20, 2025
Accepted: November 22, 2025

Errakha K., Samih A., Marzouk A., Krari A.  Exploring LSTM-CAMF: A New Approach for Context-Aware Collaborative Filtering.  Mathematical Modeling and Computing. Vol. 12, No. 4, pp. 1221–1231 (2025) 

Authors:
  1. K. Errakha
  2. A. Samih
  3. A. Marzouk
  4. A. Krari
1
Computer, Networks, Mobility and Modeling Laboratory, Hassan First University
2
Artificial Intelligence Research and Applications Laboratory, University Hassan First
3
Computer, Networks, Mobility and Modeling Laboratory, Hassan First University
4
Laboratory of Research Watch for Emerging Technologies, Hassan First University

To produce  more accurate  recommendations, Context-Aware Recommender Systems (CARS) incorporate contextual elements during user interactions.  However, a major challenge lies in the need for additional contextual data, which can hinder the performance of collaborative filtering techniques.  In this research, we introduce an innovative approach for detecting contextual information in real time by integrating Long Short-Term Memory (LSTM) recurrent neural networks with Context-Aware Matrix Factorization (CAMF).  This strategy is designed to dynamically adjust to changes in contextual conditions by modeling user relationships and their temporal evolution, ultimately aiming to boost recommendation accuracy.  The effectiveness of the proposed method is evaluated using two standard performance metrics: Mean Absolute Error (MAE), NDCG (Normalized Discounted Cumulative Gain), MSE (Mean Squared Error) and Root Mean Square Error (RMSE).

CAMF
LSTM
RMSE
MAE
CARS
  1. Samih A., Ghadi A., Fennan A.  The Impact of Covid 19 on Recommendation Platforms.  International Conference on Advanced Intelligent Systems for Sustainable Development.  19–34 (2022).
  2. Shafqat W., Byun Y.-C.  A Context-Aware Location Recommendation System for Tourists Using Hierarchical LSTM Model.  Sustainability.  12 (10), 4107 (2020).
  3. Samih A., Adadi A., Berrada M.  Towards a knowledge-based explainable recommender system.  BDIoT '19: Proceedings of the 4th International Conference on Big Data and Internet of Things.  21, 1–5 (2019).
  4. Pichl M., Zangerle E.  User models for multi-context-aware music recommendation.   Multimedia Tools and Applications.  80 (15), 22509–22531 (2021).
  5. Casillo M., Colace F., Conte D., Lombardi M., Santaniello D., Valentino C.  Context-aware recommender systems and cultural heritage: a survey.  Journal of Ambient Intelligence and Humanized Computing.  14 (4), 3109–3127 (2023).
  6. Abdi M. H., Okeyo G. O., Mwangi R. W.  Matrix Factorization Techniques for Context-Aware Collaborative Filtering Recommender Systems: A Survey.  Computer and Information Science.  11 (2), 1–10 (2018).
  7. Dey A. K.  Understanding and using context.  Personal and Ubiquitous Computing.  5 (1), 4–7 (2001).
  8. Adomavicius G., Tuzhilin A.  Context-aware recommender systems.  Recommender Systems Handbook.  217–253 (2011).
  9. Hassan A. Y., Fadel E., Akkari N.  Exponential Decay Function-Based Time-Aware Recommender System for e-Commerce Applications.  International Journal of Advanced Computer Science and Applications.  13 (10), 602–612 (2022).
  10. Lumbantoruan R., Simanjuntak P., Aritonang I., Simaremare E.  TopC-CAMF: A Top Context Based Matrix Factorization Recommender System (2022).
  11. Yadav K. K., Soni H. K., Yadav G., Sharma M.  Collaborative Filtering Hybrid Recommendation System Using Neural Network and Matrix Factorization Techniques.  International Journal of Intelligent Systems and Applications in Engineering.  12 (8s), 695–701 (2023).
  12. Samih A., Ghadi A., Fennan A.  ExMrec2vec: explainable movie recommender system based on Word2vec.  International Journal of Advanced Computer Science and Applications.  12 (8), (2021).
  13. Ali W., Kumar J., Mawuli C. B., She L., Shao J.  Dynamic context management in context-aware recommender systems.  Computers and Electrical Engineering.  107, 108622 (2023).
  14. Adomavicius G., Mobasher B., Ricci F., Tuzhilin A.  Context-aware recommender systems.  AI Magazine.  32 (3), 67–80 (2011).
  15. Casillo M., Gupta B. B., Lombardi M., Lorusso A., Santaniello D., Valentino C.  Context-Aware Recommender Systems: A Novel Approach Based on Matrix Factorization and Contextual Bias.  Electronics.  11 (7), 1003 (2022).
  16. Noor T. H., Almars A. M., Atlam E. S., Noor A.  Deep Learning Model for Predicting Consumers' Interests of IoT Recommendation System.  International Journal of Advanced Computer Science and Applications.  13 (10), 161–170 (2022).
  17. Sak H., Senior A., Beaufays F.  Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling.  Proceedings of Interspeech 2014. 338–342 (2014).
  18. Zarzour H., Jararweh Y., Hammad M. M., Al-Smadi M.  A long short-term memory deep learning framework for explainable recommendation.  2020 11th International Conference on Information and Communication Systems (ICICS).  233–237 (2020).
  19. Ahmed I., Ahmad M., Chehri A., Jeon G.  A heterogeneous network embedded medicine recommendation system based on LSTM.  Future Generation Computer Systems.  149, 1–11 (2023).
  20. Zhao C.  Deep Bi-LSTM Networks for Sequential Recommendation.  Entropy.  22 (8), 870 (2020).
  21. Kiruthika N. S., Thailambal D. G.  Dynamic Light Weight Recommendation System for Social Networking Analysis Using a Hybrid LSTM-SVM Classifier Algorithm.  Optical Memory and Neural Networks.  31 (1), 59–75 (2022).
  22. Wang J., Zhu L., Dai T., Wang Y.  Deep memory network with Bi-LSTM for personalized context-aware citation recommendation.  Neurocomputing.  410, 103–113 (2020).
  23. Lumbantoruan R., Zhou X., Ren Y., Chen L.  I-CARS: An interactive context-aware recommender system.  2019 IEEE International Conference on Data Mining (ICDM). 1240–1245 (2019).