Journals / Bilişim Teknolojileri Dergisi / 2026 / Cilt: 19 Sayı: 4

The Best Model Selection and Performance Evaluation for Product Recommendation in E-Commerce Systems

E-Ticaret Sistemlerinde Ürün Önerisi Amaçlı En İyi Model Seçimi ve Performans Değerlendirmesi

Cansu Çeri(ÜSKÜDAR ÜNİVERSİTESİ)0009-0002-7922-2695
Ersin Ersoy(Alanya Üniversitesi)0000-0002-6100-9514
Pages
529–542
Publication Date
2026-10-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The primary objective of this research is to identify the most suitable recommendation model by revealing the strengths and weaknesses of different algorithms in terms of recommendation accuray, diversity, novelty, and personalization.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:One of the most effective ways to enhance user experience and increase sales in the e-commerce sector is through recommendation systems that provide personalized product suggestions.
📊
Key Findings & Data:These systems analyze data such as users’ past interactions, purchasing habits, and product features to generate tailored recommendations.
💡
Conclusion & Impact:The primary objective of this research is to identify the most suitable recommendation model by revealing the strengths and weaknesses of different algorithms in terms of recommendation accuray, diversity, novelty, and personalization.
🔬Design:Review & Systematic Survey
📍Scope:Comprehensive Sample
⚙️Variables:e-ticaret · ürün öneri sistemleri · makine öğrenmesi

Abstract

One of the most effective ways to enhance user experience and increase sales in the e-commerce sector is through recommendation systems that provide personalized product suggestions. These systems analyze data such as users’ past interactions, purchasing habits, and product features to generate tailored recommendations. Today, advanced recommendation algorithms used by major e-commerce platforms play a critical role in boosting customer loyalty and improving conversion rates. In this study, we compare the performance of various algorithms in product recommendation systems using a uniquely constructed and authentic dataset obtained from a real e-commerce platform. While algorithms aim to provide suggestions based on individual user preferences, they employ different methods and approaches. The performance of these algorithms is comprehensively evaluated using metrics such as Mean Average Precision, Catalog Coverage, Mean Novelty Score, Mean Diversity Score and Mean Personalization Score. Based on a review of studies in the literature, this study is original research conducted on a real e-commerce company dataset, taking all of the mentioned metrics into account. The primary objective of this research is to identify the most suitable recommendation model by revealing the strengths and weaknesses of different algorithms in terms of recommendation accuray, diversity, novelty, and personalization.

Özet

E-ticaret sektöründe kullanıcı deneyimini ve satışları artırmanın en önemli yollarından biri, kullanıcılara özel ürün önerileri sunabilen öneri sistemleridir. Bu sistemler, kullanıcıların geçmiş etkileşimleri, satın alma alışkanlıkları ve ürün özellikleri gibi verileri analiz ederek kişiselleştirilmiş öneriler oluşturur. Günümüzde, büyük e-ticaret platformları tarafından kullanılan gelişmiş öneri algoritmaları, müşteri sadakatini artırmak ve dönüşüm oranlarını yükseltmek için kritik bir rol oynamaktadır. Bu çalışmada, özel olarak oluşturulmuş ve gerçek bir e-ticaret platformundan elde edilen özgün bir veri seti kullanılarak, farklı algoritmaların ürün öneri sistemlerindeki performansı karşılaştırılmıştır. Algoritmalar, her bir kullanıcının tercihlerine göre önerilerde bulunmayı hedeflerken, farklı yöntemler ve yaklaşımlar kullanmaktadır. Bu algoritmaların performansı; Ortalama Doğruluk Puanı, Katalog Kapsamı, Ortalama Yenilik Puanı, Ortalama Çeşitlilik Puanı, Ortalama Kişiselleştirme Puanı metrikleri kullanılarak kapsamlı bir şekilde değerlendirilmiştir. Literatürde yer alan çalışmalar incelendiğinde bu çalışma, söz konusu metriklerin tamamı dikkate alınarak gerçek bir e-ticaret şirketi veri seti üzerinde yapılan özgün bir çalışmadır. Çalışmanın temel amacı, farklı algoritmaların öneri doğruluğu, çeşitlilik, yenilikçilik ve kişiselleştirme açısından güçlü ve zayıf yönlerini ortaya koyarak, en uygun öneri modelini belirlemektir.

🔖

Cite This Article

Çeri, C., Ersoy, E. (2026). The Best Model Selection and Performance Evaluation for Product Recommendation in E-Commerce Systems. Bilişim Teknolojileri Dergisi, Cilt: 19 Sayı: 4, 529–542. https://doi.org/10.17671/gazibtd.1718305

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (29)

  1. X. He, Q. Liu, S. Jung, “The Impact of Recommendation System on User Satisfaction: A Moderated Mediation Approach”, ResearchGate, 2024.
  2. H. Le, Building and Evaluating Recommender Systems, Bachelor’s Thesis, Metropolia University of Applied Sciences, 2019.
  3. F. Ricci, L. Rokach, B. Shapira, and P. B. Kantor, Eds., *Recommender Systems Handbook*. Springer, 2011.
  4. G. Salton and M. J. McGill, Introduction to Modern Information Retrieval. New York: McGraw-Hill, 1983.
  5. Y. LeCun, I. Goodfellow, and A. Courville, *Deep Learning*. MIT Press, 2016.
  6. L. Breiman, “Random forests,” *Machine Learning*, vol. 45, no. 1, pp. 5–32, 2001.
  7. R. Burke, “Hybrid recommender systems: Survey and experiments,” User Modeling and User-Adapted Interaction, vol. 12, no. 4, pp. 331– 370, 2002.
  8. M. Artukarslan, S. E. Alptekin, “Collaborative Filtering Based Recommender System Design For E-Commerce: A Case Study”, ICIW 2019: The Fourteenth International Conference on Internet and Web Applications and Services, 2019.
  9. M. Anbazhagan, M. Arock, “A Study and Analysis of Collaborative Filtering Algorithms for Recommender Systems”, International Journal of Computer Technology and Applications (IJCTA), vol. 9, no. 27, pp. 127–136, 2016.
  10. K. Saini, A. Singh, “Hybrid Recommender System for E-Commerce: A Comprehensive Review and Future Directions”, Journal of Harbin Engineering University, August 2023.
  11. A. Özkılıç, E-Ticaret Sitelerine Öneri Sisteminin Uygulanması, Yüksek Lisans Tezi, Bursa Teknik Üniversitesi, Lisansüstü Eğitim Enstitüsü, 2022.
  12. N. Padhy, S. Suman, T. S. Priyadarshini, S. Mallick, “A Recommendation System for E-Commerce Products Using Collaborative Filtering Approaches”, Eng. Proc., vol. 67, pp. 50, 2024.
  13. M. Srifi, A. Oussous, A. A. Lahcen, S. Mouline, “Recommender Systems Based on Collaborative Filtering Using Review Texts—A Survey”, Information, vol. 11, no. 6, pp. 1–21, 2020.
  14. Chollet, F. Deep Learning with Python, 2nd ed., Manning Publications, 2021, Chapter 4.
  15. Raghavendra C K, Srikantaiah K.C., Venugopal K. R., “Personalized Recommendation Systems (PRES): A Comprehensive Study and Research Issues”, International Journal of Modern Education and Computer Science, vol. 10, October 2018.
  16. B. T. Betru, C. A. Onana, B. Batchakui, “Deep Learning Methods on Recommender System: A Survey of State-of-the-art”, International Journal of Computer Applications, vol. 162, no. 10, pp. 17–25, 2017.
  17. L. Legito, F. Y. Wattimena, Y. U. Rofi’i, M. Munawir, “E-Commerce Product Recommendation System Using Case-Based Reasoning (CBR) and K-Means Clustering”, Int. J. Software Eng. Comput. Sci. (IJSECS), vol. 3, no. 2, pp. 162–173, 2023.
  18. T. S. Phalle, S. Bhushan, “Content-Based Filtering and Collaborative Filtering: A Comparative Study”, Journal of Advanced Zoology,vol.45,issueS-4,pp.96-100.2024.
  19. E. Vozalis, K. G. Margaritis, “Analysis of Recommender Systems’. Algorithms”, University of Macedonia, 2003.
  20. P. Cremonesi, Y. Koren, and R. Turrin, “Performance of recommender algorithms on top-N recommendation tasks,” in *Proc. of the 4th ACM Conference on Recommender Systems (RecSys’10)*, pp. 39–46, 2010.
  21. S. B. Kotsiantis, D. Kanellopoulos, and P. E. Pintelas, “Data preprocessing for supervised learning,” *International Journal of Computer Science*, vol. 1, no. 2, pp. 111–117, 2006.
  22. G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions,” *IEEE Transactions on Knowledge and Data Engineering*, vol. 17, no. 6, pp. 734–749, 2005.
  23. L. Atkinson, Beginning PHP and MySQL: From Novice to Professional, 4th ed., Berkeley, CA: Apress, 2009.
  24. Y. Bitirim, “A Content-Based Product Recommendation Approach”, Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, vol. 37, no. 1, pp. 119–128, 2022.
  25. J. Wei, J. He, K. Chen, Z. Tang, “Collaborative Filtering and Deep Learning Based Recommendation System for Cold Start Items”, Expert Systems with Applications, October 2016.
  26. R.M. Rifqi, D. Djupriadi, W. T. Haryanto, E. Utami, A. H. Muhamad, “Hybrid Recommendation System in E-Commerce”, International Journal of Integrated Science and Technology (IJIST), 2015.
  27. S. Gheewala, S. Xu, S. Yeom, “In-depth Survey: Deep Learning in Recommender Systems—Exploring Prediction and Ranking Models, Datasets, Feature Analysis, and Emerging Trends”, Neural Computing and Applications, 2025.
  28. M. M. Alam, M. Ahmed, “Deep Learning Based Collaborative Filtering Recommendation System”, Procedia Computer Science, 2025.
  29. Kwon, G. Bak, Y. C. Bae, “A Hybrid Recommendation System Based on Similar-Price Content in a Large-Scale E-Commerce Environment”, Applied Sciences, 2025.