The Development of a Method for Forecasting the Business Valuation of Public Companies Within the Framework of the Comparative Approach Using Artificial Intelligence

The article focuses on the study of issues related to assessing the business value of publicly traded companies using artificial intelligence. The purpose of the study is to develop a model for predicting the business value of publicly traded companies within the framework of a comparative approach. The relevance of this work is that in times of uncertainty, it can be difficult to justify the market value of the business of public companies due to the fact that historical transaction prices, which are used as the basic information for calculating market value in the framework of the capital market method, may not reflect the company’s future prospects. The scientific novelty of the research consists in developing a method for predicting the business value of publicly traded companies using the main section of artificial intelligence — machine learning. The authors used the following methods in their scientific research, including logical and statistical methods (correlation analysis) and machine learning techniques such as linear regression, decision tree, tree ensembles, and recurrent neural network. The developed method consists of six stages which integrate the main steps of machine learning with the classical stages of data cost estimation. Based on the results of testing the method, eleven models of extra-random decision trees have been developed. These Trees allow us to predict the direction of movement of industry indexes Moscow Exchange depending on exogenous and technical indicators. It can be concluded that the developed models have a high level of accuracy (based on the test data R2 of 0.99 and MAPE below 1%) of forecasting industry indices and the suitability of the method for solving the problem of predicting the share price of a single public company within the context of the capital market method. The prospect of further research relates to the development of predictive models for all public companies, taking into account their financial characteristics and behavioral factors. This article will be beneficial for practicing appraisers in their evaluation of businesses in this field and for investors.

1. Leong K.-Y., Ariff M., Alireza Z., Bhatti M.I. Bank stock valuation theories: Do they explain prices based on theories? International Journal of Managerial Finance. 2023;19(2):331-350. DOI: 10.1108/IJMF-06-2021-0278

2. Pomulev A.A., Pomuleva N.S. Methodological aspects of valuation of credit institutions under external uncertainty. Finance: Theory and Practice. 2022;26(6):212-232. DOI: 10.26794/2587-5671-2022-26-6-212-232

3. Cortes C., Vapnik V.N. Support-vector networks. Machine Learning. 1995;20:273-297. DOI: 10.1007/BF00994018

4. Choi M., Lee H.J., Park S.H., Jeon S.W., Cho S. Stock price momentum modeling using social media data. Expert Systems with Applications. 2024;237C:121589. DOI: 10.1016/j.eswa.2023.121589

5. Abinanda Vrishnaa K., Sabiyath Fatima N. Tweet based sentiment analysis for stock price prediction. In: Choudrie J., Mahalle P.N., Perumal T., Joshi A., eds. ICT with intelligent applications (ICTIS 2023). Singapore: Springer; 2023:249-259. (Lecture Notes in Networks and Systems. Vol. 719). DOI: 10.1007/978-981-99-3758-5_23

6. Vu L.T., Pham D.N., Kieu H.T., Pham T.T. Sentiments extracted from news and stock market reactions in Vietnam. International Journal of Financial Studies. 2023;11(3):101. DOI: 10.3390/ijfs11030101

7. Huang C., Huang. H.-Yi., Ho K.-C. Media coverage and stock liquidity: Evidence from China. International Review of Economics & Finance. 2024;89A:665-682. DOI: 10.1016/j.iref.2023.07.085

8. Kaur R., Sharma A. Prediction of stock prices of blue-chip companies using machine learning algorithms. International Journal of Business Intelligence and Data Mining. 2023;23(4): 375-395. DOI: 10.1504/ijbidm.2023.134316

9. Low P.R., Sakk E. Comparison between autoregressive integrated moving average and long short term memory models for stock price prediction. IAES International Journal of Artificial Intelligence (IJ-AI). 2023;12(4):1828-1835. DOI: 10.11591/ijai.v12.i4.pp1828-1835

10. Gülmez B. Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm. Expert Systems with Applications. 2023;227:120346. DOI: 10.1016/j.eswa.2023.120346

11. Li Q., Kamaruddin N., Al-Jaifi H.A. Forecasting stock prices changes using long-short term memory neural network with symbolic genetic algorithm. Research Square. 2023. DOI: 10.21203/rs.3.rs-3284486/v1

12. Hang L., Liu D., Xie F.A Hybrid model using PCA and BP neural network for time series prediction in Chinese Stock Market with TOPSIS analysis. Scientific Programming. 2023:1-15. DOI: 10.1155/2023/9963940

13. Chen C., Xue L., Xing W. Research on improved GRU-based stock price prediction method. Applied Sciences. 2023;13(15):8813. DOI: 10.3390/app13158813

14. Shet A., Ashika S., Hanumanth D.N., Shetty S., Ranganatha K. Stock price prediction using machine learning. International Journal of Engineering Applied Sciences and Technology. 2022;7(2):225-228. DOI: 10.33564/ijeast.2022.v07i02.034

15. Sarkar M., Pratima M. N., Darshan R., Chakraborty D., Agrebi M. An intelligent model for identifying fluctuations in the stock market and predicting investment policies with guaranteed returns. In: Sharma R., Jeon G., Zhang Y., eds. Data analytics for Internet of things infrastructure. Internet of things. Cham: Springer; 2023:91-115. DOI: 10.1007/978-3-031-33808-3_6

16. Ibrahim A.A., Noori B., Fadil M.A. Forecasting stock prices with an integrated approach combining ARIMA and machine learning techniques ARIMAML. Journal of Computer and Communications. 2023;11(8):58-70 DOI: 10.4236/jcc.2023.118005

17. Karthikeyan C., Anselin Nisha S., Anandan P., et al. Predicting stock prices using machine learning techniques. In: 6 th Int. conf. on inventive computation technologies (ICICT). New York, NY: IEEE; 2021:1-5. DOI: 10.1109/ICICT50816.2021.9358537

18. Dobrina M.V., Strekalova D.S. Forecasting the closing price of stocks in Python. In: Economic forecasting: Models and methods. Proc. 17 th Int. sci.-pract. conference (Voronezh, December 22–23, 2021). Voronezh: Voronezh State University; 2022:109-112. (In Russ.).

19. Treboganov P.M. Trading agents with reinforcement learning. Nauchnye zapiski molodykh issledovatelei = Scientific Notes of Young Scientists. 2020;8(6):46-57. (In Russ.).

20. Prastika J., Ardiansyah M., Pangaribuan C.H., Putra O.P., Hidayat D. The impact of firm financial fundamentals on stock performance: An empirical evidence on Indonesian telecommunication sector. E3S Web of Conferences. 2023;426:02140. DOI: 10.1051/e3sconf/202342602140

21. Hendawy E., McMillan D.G., Sakr Z.M., Shahwan T.M. Relative informative power and stock return predictability: A new perspective from Egypt. Journal of Financial Reporting and Accounting. 2023. DOI: 10.1108/jfra-02-2023-0076

22. Jeevan В., Naresh E., Kumar B.P., Kambli P. Share price prediction using machine learning technique. In: 3 rd Int. conf. on circuits, control, communication and computing (I4C). (Bangalore, October 13-05, 2018). New York, NY: IEEE; 2018:1-4. DOI: 10.1109/CIMCA.2018.8739647

23. Koklev P.S. Business valuation with machine learning. Finance: Theory and Practice. 2022;26(5):132-148. DOI: 10.26794/2587-5671-2022-26-5-132-148

24. Chen X., Cho Y.H., Dow Y., Lev B. Predicting future earnings changes using machine learning and detailed financial data. Journal of Accounting Research. 2022;60(2):467-515. DOI: 10.1111/1475-679X.12429

25. Guner P.U., Unal S.N. An artificial neural network based method for company valuation. Journal of Business, Economics and Finance. 2023;12(2):91-101. DOI: 10.17261/Pressacademia.2023.1741

26. Geertsema P., Lu H. Relative valuation with machine learning. Journal of Accounting Research. 2023;61(1):329-376. DOI: 10.1111/1475-679X.12464

27. Zhang R., Tian Z., McCarthy K.J., Wang X., Zhang K. Application of machine learning techniques to predict entrepreneurial firm valuation. Journal of Forecasting. 2023;42(2):402-417. DOI: 10.1002/for.2912

28. Valčić S.B., Crnković-Stumpf B., Katunar J. Business valuation in oil&gas industry: New challenges. In: 36 th Int. convent. on information and communication technology, electronics and microelectronics (MIPRO). (Opatija, May 20–24, 2013). New York, NY: IEEE; 2013. URL: https://www.researchgate.net/publication/261431751_Business_valuation_in_oilGas_industry_New_challenges (accessed on: 05.10.2024).

29. Budennyy S., Kazakov A., Kovtun E., Zhukov L. New drugs and stock market: A machine learning framework for predicting pharma market reaction to clinical trial announcements. Scientific Reports. 2023;13:12817. DOI: 10.1038/s41598-023-39301-4

30. Frolovichev A.I., Denisova O.Yu., Golevko E.V. Forecasting the value of shares of Russian companies depending on the dollar exchange rate and oil price on the example of PJSC TransContainer. In: Actual problems of economic and financial management of transport companies. Proc. Nat. sci.-pract. conf. Vol. II. Moscow: Art-Business-Center; 2016:297-302. (In Russ.).

31. Sopelnik E.Yu., Fedoseeva L.V. Comparison of technical and fundamental indicators in stock price forecasting. Upravlencheskii uchet = The Management Accounting Journal. 2021;(2-2):284-291. (In Russ.).

32. Galkin I.N. Estimation and analysis of corporate value using machine learning methods. Finansovye rynki i banki = Financial Markets and Banks. 2024;(4):188-192. (In Russ.).

33. Copeland T., Koller T., Murrin J. Valuation: Measuring and managing the value of companies. New York,NY.: John Wiley & Sons; 1990. 512 p. (Russ. ed.: Copeland T., Koller T., Murrin J. Stoimost’ kompanii: otsenka i upravlenie. Moscow: Olymp-Business; 2005. 576 p.).

34. Pomulev A.A. Methodological grounds for using behavioral finance tools in the process of assessing the value of a business. Finansovye rynki i banki = Financial Markets and Banks. 2024;(8):142-147. (In Russ.).

35. Bogatyrev S.Yu., Nikonova I.A., Pomulev A.A. Machining technologies to compute the psychological-financial index. Finansy i kredit = Finance and Credit. 2024;30(4):788-813. (In Russ.). DOI: 10.24891/fc.30.4.788

36. Sinsomboonthong S. Performance comparison of new adjusted min-max with decimal scaling and statistical column normalization methods for artificial neural network classification. International Journal of Mathematics and Mathematical Sciences. 2022. DOI: 10.1155/2022/3584406

37. Albon C. Machine learning with Python cookbook: Practical solutions from preprocessing to deep learning. Sebastopol, CA: O’Reilly Media; 2018. 364 p. (In Russ.: Albon C. Mashinnoe obuchenie s ispol’zovaniem Python. Sbornik retseptov. St. Petersburg: BHV; 2022. 384 p.).