Flag Counter
AKILLI SİSTEMLER VE UYGULAMALARI DERGİSİ
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.

Building A Hybrid Recommendation System For E-Commerce

E-Ticaret için Hibrit Öneri Sistemleri

How to cite: Şimşek H, Yeniad M. Building a hybrid recommendation system for e-commerce. Akıllı Sistemler ve Uygulamaları Dergisi (Journal of Intelligent Systems with Applications) 2022; 5(1): 4-7. DOI: 10.54856/jiswa.202205190

Full Text: PDF, in English.

Total number of downloads: 486

Title: Building A Hybrid Recommendation System For E-Commerce

Abstract: With the technology occupying a large place in human life, our shopping habits have also changed drastically. Increasing product variety and alternatives have made it difficult for people to reach products that suit their own tastes. Thanks to the Suggestion Systems, it has made internet shopping easier by using the evaluation, comment and scoring criteria of other users who have used the same or similar products to the products they are interested in. By learning the tendencies of the users while choosing the products, the presentation of the appropriate products enabled the users to reach their requests easily and quickly. At the same time, it has become mandatory for e-commercial companies to learn the preferences of users in order to compete with other companies. In this study, the most popular recommendation systems and algorithms used in e-commerce platforms are compared.

Keywords: recommendation systems; hybrid recommendation systems for e-commerce; e-commerce shoppings


Başlık: E-Ticaret için Hibrit Öneri Sistemleri

Özet: Teknolojinin insan hayatında büyük bir yer tutmasıyla birlikte alışveriş alışkanlıklarımız da büyük ölçüde değişti. Artan ürün çeşitliliği ve alternatifleri insanların kendi zevklerine uygun ürünlere ulaşmasını zorlaştırmıştır. Öneri Sistemleri sayesinde, ilgilendikleri ürünlerle aynı veya benzer ürünleri kullanmış diğer kullanıcıların değerlendirme, yorum ve puanlama kriterlerini kullanarak internet alışverişini kolaylaştırmıştır. ürünler, uygun ürünlerin sunumu kullanıcıların isteklerine kolay ve hızlı bir şekilde ulaşmasını sağlamıştır. Aynı zamanda e-ticaret firmalarının diğer firmalarla rekabet edebilmesi için kullanıcıların tercihlerini öğrenmesi zorunlu hale gelmiştir. Bu çalışmada, e-ticaret platformlarında kullanılan en popüler öneri sistemleri ve algoritmaları karşılaştırılmıştır.

Anahtar kelimeler: öneri sistemleri; e-ticaret için hibrit öneri sistemleri; e-ticaret alışverişleri


Bibliography:
  • Rodriguez G. Introduction to recommender systems. 2018, Retrieved from https://tryolabs.com/blog/introduction-to-recommender-systems/
  • Dwivedi R. What are recommendation systems in machine learning? 16 April 2020. [Online]. Retrieved from https://www.analyticssteps.com/blogs/what-are-recommendation-systems-machine-learning
  • Rocca B. Introduction to Recommender Systems. June 3, 2019. Retrieved from https://towardsdatascience.com/introduction-to-recommender-systems-6c66cf15ada
  • Cilingir I. Recommendation Systems. June 24, 2019. Retrieved from https://medium.com/@irmcilingir/%C3%B6neri-sistemleri-recommendation-systems-28a3f341c0a9
  • Le J. The 4 Recommendation Engines That Can Predict Your Movie Tastes. May 1, 2018. Retrieved from https://towardsdatascience.com/the-4-recommendation-engines-that-can-predict-your-movie-tastes-109dc4e10c52
  • Allen RB. User models: Theory, method, and practice. International Journal of Man-Machine Studies 1990; 32(5): 511-543.
  • Ozkok H. Recommendation Engine. April 17, 2020. Retrieved from https://www.datasciencearth.com/recommendation-engine-tavsiye-oneri-sistemleri/
  • Guler S. Recommendation Systems and the Usage of Recommendation Systems in E-commerce. MSc Thesis, Sakarya University, 2019.
  • Papagelis M, Plexousakis D, Kutsuras T. Alleviating the sparsity problem of collaborative filtering using trust inferences. In iTrust'05 Proceeding of Third International Conference on Trust Management, May 2005, pp. 224-239.
  • Bobadilla J, Ortega F, Hernando A, Bernal J. A collaborative filtering approach to mitigate the new user cold start problem. Knowledge-based systems 2012; 26: 225-238.