Forecasting the Financial Efficiency of Russian Cinema Using a Multifactor Ensemble Machine Learning Model Trained on Historical Data

The object of the study is data on the distribution of Russian cinema films from July 2022 to September 2023. Specifically, it analyzes 185 films that were released during this period. The research tool consists of 26 and 146-factor machine learning models that have been pre-trained based on previous periods (from 2004 to July 2022, with 1,500 films).

The purpose of the study is to demonstrate that machine learning models, trained on historical data, can accurately predict future data, which is especially important for funding programs aimed at developing national cinema in the Russian Federation and attracting private investment, in light of the departure of foreign film distributors from the film market. The study used methods to evaluate film projects based on their historical profitability using rental indicators and the characteristics of the creative teams involved in producing them. The emphasis is on ensemble models –AdaBoost, Bagging, ExtraTrees, GradientBoosting, RandomForest, Stacking, Voting, XGBoost, CatBoost.

The novelty of this research lies in introducing of new sources into the scientific community and the potential for practical application of the developed methods for both public and private investors to evaluate film projects prior to the start of the production cycle.

Conclusions: Conclusions: Based on the analysis of the quality metrics (accuracy, ROC AUC, and others) for a sample of 185 newly released films (through September 2023), we found that the drop in these metrics was not significant. This suggests that it is possible to use pre-trained models based on historical data to make predictions about fees and other rental outcomes. By analyzing the past work of the project director, screenwriters, cameramen, producers, artists, editor, composer and key actors of the project, estimated distribution data, and the amount of project funding, it is possible to make an accurate prediction about the success of a film. This will allow you to see the total fees, payback period, number of views, and viewer rating.

1. Paul C., Das P. K. Predicting movie revenue before committing significant investments. Journal of Media Economics. 2022;34(2):63–90. DOI: 10.1080/08997764.2022.2066108

2. Mbunge E., Fashoto S. G., Bimha H. Prediction of box-office success: A review of trends and machine learning computational models. International Journal of Business Intelligence and Data Mining. 2022;20(2):192–207. DOI: 10.1504/IJBIDM.2022.120825

3. Tantawichien J., Mizuyama H., Nonaka T. Designing a human computation game for enhancing early-phase movie box office prediction. In: Hamada R., et al. Neo-simulation and gaming toward active learning. Singapore: Springer; 2019:13–22. (Translational Systems Sciences. Vol. 18.). DOI: 10.1007/978–981–13–8039–6-2

4. Pirunthavi V., Vithusia R. P., Abishankar K., Ekanayake E. M., Yanusha M. Movie success and rating prediction using data mining algorithms. In: Int. res. conf. of Uva Wellassa University (IRCUWU-2020) “Sustainable business transition through information and knowledge dissemination”. Badulla: Uva Wellassa University; 2020:175–176. URL: https://www.uwu.ac.lk/wp-content/uploads/2020/proceeding-of-ircuwu2020-v2.pdf

5. Chakraborty P., Rahman Z., Rahman S. Movie success prediction using historical and current data mining. International Journal of Computer Applications. 2019;178(47):1–5. DOI: 10.5120/ijca2019919415

6. Murschetz P. C., Bruneel C., Guy J. L., et al. Movie industry economics: How data analytics can help predict movies’ financial success. Nordic Journal of Media Management. 2020;1(3):339–359. DOI: 10.5278/njmm.2597–0445.5871

7. Bruneel C., Guy J.-L., Haughton D., et al. Movie analytics and the future of film finance. Are Oscars and box office revenue predictable? In: Murschetz P., Teichmann R., Karmasin M., eds. Handbook of state aid for film. Media business and innovation. Cham: Springer; 2018:551–578. DOI: 10.1007/978–3–319–71716–6-30

8. Ruus R., Sharma R. Predicting movies’ box office result — a large scale study across Hollywood and Bollywood. In: Cherifi H., Gaito S., Mendes J., Moro E., Rocha L., eds. Complex networks and their applications VIII. (COMPLEX NETWORKS 2019). Cham: Springer; 2020:982–994. (Studies in Computational Intelligence. Vol. 882). DOI: 10.1007/978–3–030–36683–4-78

9. Adekola O. D., Maitanmi S. O., Kasali F. A., et al. Movie success prediction using data mining. British Journal of Computer, Networking and Information Technology. 2021;4(2):22–30. DOI: 10.52589/BJCNIT-CQOCIREC

10. Namlı Ö., Ozcan T. Forecasting of box office revenue using machine learning algorithms. Yönetim Bilişim Sistemleri Dergisi. 2017;(3):130–143.

11. Wang Z., Zhang J., Ji S., et al. Predicting and ranking box office revenue of movies based on Big Data. Information Fusion. 2020;60:25–40. DOI: 10.1016/j.inffus.2020.02.002

12. Shahid M. H., Islam M. A. Investigation of time series-based genre popularity features for box office success prediction. The Open Access Journal for Computer Science. 2023;9: e1603. DOI: 10.7717/peerj-cs.1603

13. Dozhdikov A. Prediction of the results of movie release using machine learning. Voprosy teoreticheskoi ekonomiki = Theoretical Economics. 2023;(4):93–114. (In Russ.). DOI: 10.52342/2587–7666VTE-2023-4-93-114

14. Dozhdikov A. V. Determination of investment success and its factors for Russian cinema at the box office using machine learning. Finance: Theory and Practice. 2024;28(1):188–203. DOI: 10.26794/2587–5671–2024–28–1–188–203

15. Abidi S. M.R., Xu Y., Ni J., Wang X., Zhang W. Popularity prediction of movies: From statistical modeling to machine learning techniques. Multimedia Tools and Applications. 2020;79(4):35583–35617. DOI: 10.1007/s11042–019–08546–5

16. Li D., Liu Z.-P. Predicting box-office markets with machine learning methods. Entropy. 2022;24(5):711. DOI: 10.3390/ e24050711

17. Qin M., Zhou Q., Chen W., Zhao L. MAMRP: Multi-modal data aware movie rating prediction. In: Yang X., et al. Advanced data mining and applications (ADMA 2023). Cham: Springer; 2023:660–675. (Lecture Notes in Computer Science. Vol. 14177). DOI: 10.1007/978–3–031–46664–9-44

18. Lu S.-H., Wang H.-J., Nguyen A. T. Machine learning applications on box-office revenue forecasting: The Taiwanese film market case study. In: Optimal transport statistics for economics and related topics. Cham: Springer; 2023:384–402. (Studies in Systems, Decision and Control. Vol. 483). DOI: 10.1007/978–3–031–35763–3-49

19. Gore M., Sheth A., Abbad S., Jain P., Mishra P. IMDB box office prediction using machine learning algorithms. International Journal for Research in Applied Science and Engineering Technology. 2022;10(5):2438–2442. DOI: 10.22214/ijraset.2022.42653

20. Kang D. Box-office forecasting in Korea using search trend data: A modified generalized Bass diffusion model. Electronic Commerce Research. 2021;21(3):41–72. DOI: 10.1007/s10660–020–09456–7

21. Li Na., Xia L. Correlation analysis of network Big Data and film time-series data based on machine learning algorithm. Mathematical Problems in Engineering. 2022. DOI: 10.1155/2022/4067554

22. Yoo B.-K., Kim S.-H. Movie box offi ce prediction at the distribution stage using text mining of movie reviews. The Korean Logistics Research Association. 2023;33(1):95–105. DOI: 10.17825/klr.2023.33.1.95

23. Quader N., Gani O., Chaki D. Performance evaluation of seven machine learning classifi cation techniques for movie box offi ce success prediction. In: 3rd Int. conf. on electrical information and communication technology (EICT). (Khulna, December 7–9, 2017). New York, NY: IEEE; 2017:1–6. DOI: 10.1109/EICT.2017.8275242

24. Lee K., Park J., Kim I., Choi Y. Predicting movie success with machine learning techniques: Ways to improve accuracy. Information Systems Frontiers. 2018;20(3):577–588. DOI: 10.1007/s10796–016–9689-z

25. Hu Y.-H., Shiau W.-M., Shih S.-P., Chen C.-J. Considering online consumer reviews to predict movie box-office performance between the years 2009 and 2014 in the US. The Electronic Library. 2018;36(6):1010–1026. DOI: 10.1108/EL-02–2018–0040

26. Gürbüz A., Biçer E., Kaya T. Prediction of gross movie revenue in the Turkish box offi ce using machine learning techniques. In: Kahraman C., et al., eds. Intelligent and fuzzy systems (INFUS 2022). Cham: Springer; 2022:86–92. (Lecture Notes in Networks and Systems. Vol. 505). DOI: 10.1007/978–3–031–09176–6-10

27. Ni Y., Dong F., Zou M., Li W. Movie box office prediction based on multi-model ensembles. Information. 2022;13(6):299. DOI: 10.3390/info13060299

28. Lee S., Bikash K. C., Choeh J. Y. Comparing performance of ensemble methods in predicting movie box offi ce revenue. Heliyon. 2020;6(6): e04260. DOI: 10.1016/j.heliyon.2020.e04260

29. Park J. H., Lim C. Predicting movie audience with stacked generalization by combining machine-learning algorithms. Communications for Statistical Applications and Methods. 2021;28(3):217–232. DOI: 10.29220/CSAM.2021.28.3.217

30. Dutta S., Dasgupta K. A shallow approach to gradient boosting (XGBoosts) for prediction of the box offi ce revenue of a movie. In: Proc. Int. conf. on innovations in software architecture and computational systems. Singapore: Springer; 2021:207–219. DOI: 10.1007/978–981–16–4301–9-16

31. Su Y., Zhang Y., Yan J. Neural network based movie rating prediction. In: Proc. Int. conf. on Big Data and computing (ICBDC’18). (Shenzhen, April 28–30, 2018). New York, NY: Association for Computing Machinery; 2018:33–37. DOI: 10.1145/3220199.3220204

32. Ru Y., Li B., Chai J. An effective daily box offi ce prediction model based on deep neural networks. Cognitive Systems Research. 2018;52:182–191. DOI: 10.1016/j.cogsys.2018.06.018

33. Wang W., Xiu J., Yang Z., Liu C. A deep learning model for predicting movie box offi ce based on deep belief network. In: Tan Y., Shi Y., Tang Q., eds. Advances in swarm intelligence (ICSI 2018). Cham: Springer; 2018:530–541. (Lecture Notes in Computer Science. Vol. 10942). DOI: 10.1007/978–3–319–93818–9-51

34. Lu W., Zhang X., Zhan X. Movie box offi ce prediction based on IFOA-GRNN. Discrete Dynamics in Nature and Society. 2022:3690077. DOI: 10.1155/2022/3690077