ДОСЛІДЖЕННЯ МЕТОДІВ ПОБУДОВИ РЕКОМЕНДАЦІЙНИХ СИСТЕМ В МЕРЕЖІ ІНТЕРНЕТ
Е. В. Мелешко, С. Г. Семенов, V. D. Khokh · Системи управління навігації та зв’язку Збірник наукових праць · 2018
The paper considers the main types of recommender systems on the Internet, based on the methods of , content-based andcollaborative filtering. The article examines ways to collect user data from web-resources that is needed to formulate recommendations. Methods of constructing classifiers for content-based filtering were investigated. Methods of calculating the similaritycoefficient of users or objects in collaborative filtering are also researched.
Cited by 14 works. doi:10.26906/sunz.2018.1.131 Open-access PDF
Authors
References
- Content-boosted collaborative filtering for improved recommendations
- Multiple Attribute Decision Making
- Business process definition
- ДОСЛІДЖЕННЯ МЕТОДІВ ПОБУДОВИ РЕКОМЕНДАЦІЙНИХ СИСТЕМ В МЕРЕЖІ ІНТЕРНЕТ
- International Market Segmentation across Consumption and Communication Categories: Identity, Demographics, and Consumer Decisions and Online Habits