Neural network-based recommendation system for content selection in online movie theatres
https://doi.org/10.35266/1999-7604-2024-4-4
Abstract
The article describes a comparative analysis using the following quality assessment criteria: system load, RAM consumption, time spent on training, RMSE (Root Mean Square Error), MAE (Mean Absolute Error), FCP (First Contentful Paint) and MSE (Mean Square Error). Using mathematical decision-making methods, the most practical algorithm was selected, a system based on DLRM (Deep Learning Recommendation Model) architecture, which showed the best results in terms of accuracy and fl exibility in processing large amounts of data, despite having high resource intensiveness. The implementation of the selected algorithm included the development of the algorithm itself, database design, creation of a graphical user interface and development.
About the Authors
K. E. Kozhikhova
Surgut State University, Surgut
Russian Federation
Russian Federation
Postgraduate
D. V. Tarakanov
Surgut State University, Surgut
Russian Federation
Russian Federation
Candidate of Sciences (Engineering), Docent
I. V. Chaley
“Surgutneftegas” PJSC, Surgut
Russian Federation
Russian Federation
Doctor of Sciences (Engineering), Professor
References
1. Глубокое погружение в рекомендательную систему Netfl ix. Хабр : офиц. сайт. URL: https://habr.com/ru/articles/677396/ (дата обращения: 24.06.2024).
2. 10 Remarkable Real-World Examples of Recommender Systems. URL: https://appstekcorp.com/blog/10-remarkable-real-world-examples-of-recommend-er-systems/ (дата обращения: 24.06.2024).
3. Deep Dive into Netfl ix’s Recommender System. Medium. URL: https://towardsdatascience.com/deep-dive-into-netflixs-recommender-system-341806ae3b48 (дата обращения: 24.06.2024).
4. How retailers can keep up with consumers. URL: https://www.mckinsey.com/industries/retail/our-in-sights/how-retailers-can-keep-up-with-consumers (дата обращения: 24.06.2024).
5. Recommender systems: benefits and practical guidelines for software professionals. URL: https://swforum.eu/online-sw-forum/software-technology/6/recommender-systems-benefits-and-practical-guidelines (дата обращения: 24.06.2024).
6. Python: Skillfactory media. Честные истории о карьере в IT. URL: https://blog.skillfactory.ru/glossary/python/ (дата обращения: 24.06.2024).
7. Библиотека NumPy: всё, что нужно знать новичку. URL: https://skillbox.ru/media/code/biblioteka-numpy-vsye-chto-nuzhno-znat-novichku/ (дата обра- щения: 24.06.2024).
8. Работаем с Pandas: основные понятия и реальные данные. URL: https://skillbox.ru/media/code/rabotaem-s-pandas-osnovnye-ponyatiya-i-realnye-dannye/ (дата обращения: 24.06.2024).
9. Библиотека Scikit-learn: как создать свой первый ML-проект. Skillbox. URL: https://skillbox.ru/media/code/biblioteka-scikitlearn-kak-sozdat-svoy-pervyy-mlproekt/ (дата обращения: 24.06.2024).
10. Keras: библиотека глубокого обучения на Python. URL: https://ru-keras.com/home/ (дата обращения: 24.06.2024).
11. Overview. A Python scikit for recommender systems. URL: https://surpriselib.com/ (дата обращения: 24.06.2024).
12. csv – CSV File Reading and Writing. URL: https:// docs.python.org/3/library/csv.html (дата обращения: 24.06.2024).
13. Библиотека os. Все о Python. Программирование на Python 3. URL: https://all-python.ru/osnovy/os.html (дата обращения: 24.06.2024).
14. time – Time access and conversions. URL: https://docs.python.org/3/library/time.html (дата обращения: 24.06.2024).
15. psutil documentation. URL: https://psutil.readthedocs.io/en/latest/index.html (дата обращения: 24.06.2024).
16. Фреймворк Flask: как он работает и зачем нужен. URL: https://skillbox.ru/media/code/freymvork-flask-kak-on-rabotaet-i-zachem-nuzhen/ (дата обращения: 24.06.2024).
17. How to Connect and Operate PostgreSQL with Python Using psycopg2 Lib. URL: https://geekpython.in/integrate-postgresql-database-in-python (дата обращения: 24.06.2024).
18. tkinter – Python interface to Tcl/Tk. URL: https://docs.python.org/3/library/tkinter.html (дата обращения: 24.06.2024).
19. pickle – Python object serialization. URL: https://docs.python.org/3/library/pickle.html (дата обращения: 24.06.2024).
20. GUI: Skillfactory media. Честные истории о карьере в IT. URL: https://blog.skillfactory.ru/glossary/gui/ (дата обращения: 24.06.2024).
Review
For citations:
Kozhikhova K.E., Tarakanov D.V., Chaley I.V. Neural network-based recommendation system for content selection in online movie theatres. Proceedings in Cybernetics. 2024;23(4):34-52. (In Russ.) https://doi.org/10.35266/1999-7604-2024-4-4
Views:
85
Email this article 