Research Article
BibTex RIS Cite

Hybrid Visual-Textual Product Recommendation System for E-Commerce Platforms

Year 2025, Volume: 5 Issue: 1, 1 - 6, 16.06.2025
https://doi.org/10.54569/aair.1700682

Abstract

Today, e-commerce sites provide a large number of products to users. However, presenting the right products to users is important for both customer satisfaction and increasing company revenues. Recommendation systems are systems that offer personalized product suggestions by analyzing user preferences and behaviors. This study presents a novel hybrid product recommendation system that integrates collaborative filtering and content-based filtering methods, enhanced by deep learning techniques. By using both visual and textual product features through BERT and CLIP models, our system addresses cold-start problem and real-time performance constraints. The system has been successfully deployed on the Cimri e-commerce platform, providing personalized recommendations that adapt to evolving user preferences while maintaining computational efficiency.

References

  • Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction, 12(4), 331–370. https://doi.org/10.1023/A:1021240730564
  • Gómez-Uribe, C. A., & Hunt, N. (2016). The Netflix recommender system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems, 6(4), 1–19. https://doi.org/10.1145/2843948
  • Resnick, P., & Varian, H. R. (1997). Recommender systems. Communications of the ACM, 40(3), 56–58. https://doi.org/10.1145/245108.245121
  • Ricci, F., Rokach, L., & Shapira, B. (2015). Recommender Systems Handbook (2nd ed.). Springer. https://doi.org/10.1007/978-1-4899-7637-6
  • Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Journal of Computer Science and Technology, 22(3), 33-42..
  • Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL'19.
  • Jong Wook Kim. Learning Transferable Visual Models From Natural Language Supervision. Arxiv. 2021
  • Huang, H., & Wang, S. (2021). Text-Visual Matching for Cross-Modal Retrieval: A Comprehensive Review. Information Fusion, 69, 71-84.
  • Kang, W., McAuley, J., & Leskovec, J. (2018). Discovering Temporal Structures in Recommendation Models. WSDM'18.
  • Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to Information Retrieval. Cambridge University Press.
  • Ricci, F., Rokach, L., & Shapira, B. (2011). Introduction to Recommender Systems Handbook. Springer.

E-Ticaret Platformları için Hibrit Görsel-Metinsel Ürün Öneri Sistemi

Year 2025, Volume: 5 Issue: 1, 1 - 6, 16.06.2025
https://doi.org/10.54569/aair.1700682

Abstract

Günümüzde e-ticaret siteleri çok sayıda ürünü kullanıcılara sunmaktadır. Ancak kullanıcılara doğru ürünlerin sunulması hem müşteri memnuniyeti hem de şirket gelirlerinin artırılması için önemlidir. Öneri sistemleri, kullanıcı tercihlerini ve davranışlarını analiz ederek kişiselleştirilmiş ürün önerileri sunan sistemlerdir. Bu çalışma, işbirlikçi filtreleme ve içerik tabanlı filtreleme yöntemlerini bütünleştiren, derin öğrenme teknikleriyle geliştirilmiş yeni bir hibrit ürün öneri sistemi sunmaktadır. BERT ve CLIP modelleri aracılığıyla hem görsel hem de metinsel ürün özelliklerini kullanan sistemimiz, soğuk başlatma sorununu ve gerçek zamanlı performans kısıtlamalarını ele almaktadır. Sistem, Cimri e-ticaret platformunda başarıyla uygulanmış olup, hesaplama verimliliğini korurken gelişen kullanıcı tercihlerine uyum sağlayan kişiselleştirilmiş öneriler sunmaktadır.

References

  • Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction, 12(4), 331–370. https://doi.org/10.1023/A:1021240730564
  • Gómez-Uribe, C. A., & Hunt, N. (2016). The Netflix recommender system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems, 6(4), 1–19. https://doi.org/10.1145/2843948
  • Resnick, P., & Varian, H. R. (1997). Recommender systems. Communications of the ACM, 40(3), 56–58. https://doi.org/10.1145/245108.245121
  • Ricci, F., Rokach, L., & Shapira, B. (2015). Recommender Systems Handbook (2nd ed.). Springer. https://doi.org/10.1007/978-1-4899-7637-6
  • Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Journal of Computer Science and Technology, 22(3), 33-42..
  • Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL'19.
  • Jong Wook Kim. Learning Transferable Visual Models From Natural Language Supervision. Arxiv. 2021
  • Huang, H., & Wang, S. (2021). Text-Visual Matching for Cross-Modal Retrieval: A Comprehensive Review. Information Fusion, 69, 71-84.
  • Kang, W., McAuley, J., & Leskovec, J. (2018). Discovering Temporal Structures in Recommendation Models. WSDM'18.
  • Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to Information Retrieval. Cambridge University Press.
  • Ricci, F., Rokach, L., & Shapira, B. (2011). Introduction to Recommender Systems Handbook. Springer.
There are 11 citations in total.

Details

Primary Language English
Subjects Natural Language Processing
Journal Section Research Article
Authors

Pınar Süngü İşiaçik This is me 0000-0002-9234-8586

Onur Tunali This is me 0000-0002-2326-0708

Emre Tekelioğlu 0009-0001-7619-1267

Ali Hakan Işik 0000-0003-3561-9375

Early Pub Date June 16, 2025
Publication Date June 16, 2025
Submission Date May 25, 2025
Acceptance Date May 29, 2025
Published in Issue Year 2025 Volume: 5 Issue: 1

Cite

IEEE P. Süngü İşiaçik, O. Tunali, E. Tekelioğlu, and A. H. Işik, “Hybrid Visual-Textual Product Recommendation System for E-Commerce Platforms”, Adv. Artif. Intell. Res., vol. 5, no. 1, pp. 1–6, 2025, doi: 10.54569/aair.1700682.

88x31.png
Advances in Artificial Intelligence Research is an open access journal which means that the content is freely available without charge to the user or his/her institution. All papers are licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which allows users to distribute, remix, adapt, and build upon the material in any medium or format for non-commercial purposes only, and only so long as attribution is given to the creator.

Graphic design @ Özden Işıktaş