This article presents a comparative study of gradient boosting and fully connected neural networks for solving the problem of binary classification of user review helpfulness on the Steam platform. Using a sample of over 6.4 million records, the effectiveness of both approaches when working with sparse text features is analyzed.
Machine learning, gradient boosting, XGBoost, neural networks, text classification, TF-IDF, review analysis
1. Voroncov K.V. Matematicheskie metody obucheniya po precedentam (teoriya mashinnogo obucheniya). - URL: http://www.machinelearning.ru/wiki/images/6/6d/Voron-ML-1.pdf (data obrascheniya: 15.02.2026).
2. Flah P. Mashinnoe obuchenie. Nauka i iskusstvo postroeniya algoritmov, kotorye izvlekayut znaniya iz dannyh. - M.: DMK Press, 2015. - 400 s.
3. Chen T., Gestrin K. XGBoost: Masshtabiruemaya sistema bustinga derev'ev / Chen T., Gestrin K. // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. - 2016. - S. 785–794. DOI: https://doi.org/10.1145/2939672.2939785
4. Nikolenko S.I., Kadurin A.A., Arhangel'skaya E.O. Glubokoe obuchenie. Pogruzhenie v mir neyronnyh setey. / Nikolenko S.I., Kadurin A.A., Arhangel'skaya E.O. - SPb.: Piter, 2020. - 480 s.
5. Novikova T.P. Razrabotka algoritma kolichestvennogo investirovaniya na baze Random Forest / T.P. Novikova, S.A. Evdokimova, U Gocuy // Modelirovanie sistem i processov. – 2022. – T. 15, № 1. – S. 53-60. DOI: https://doi.org/10.12737/2219-0767-2022-15-4-53-60
6. Manning K., Raghavan P., Shyutce H. Vvedenie v informacionnyy poisk. / Manning K., Raghavan P., Shyutce H. - M.: Vil'yams, 2011. - 528 s.
7. Pal'mov S.V. Analiz tonal'nosti tekstov: metody i prilozheniya // Programmnaya inzheneriya. - 2018. - № 9. - S. 417–425.
8. Gudfellou Ya., Bendzhio I., Kurvill' A. Glubokoe obuchenie / Gudfellou Ya., Bendzhio I., Kurvill' A. - M.: DMK Press, 2018. - 652 s.
9. Korshunov A.V., Gomzin A.G. Tematicheskoe modelirovanie tekstov na estestvennom yazyke / Korshunov A.V., Gomzin A.G. // Trudy ISP RAN. - 2012. - T. 23. DOI: https://doi.org/10.15514/ISPRAS-2012-23-13
10. Provost F., Fosett T. Data Science dlya biznesa. - URL: https://www.researchgate.net/publication/256438799_Data_Science_for_Business (data obrascheniya: 14.02.2026).
11. Shitikov V.K., Mastickiy S.E. Klassifikaciya, regressiya i drugie algoritmy intellektual'nogo analiza dannyh s ispol'zovaniem R. / Shitikov V.K., Mastickiy S.E. - URL: https://github.com/ranalytics/data-mining (data obrascheniya: 17.02.2026).
