Business Valuation with Machine learning

The aim of the article is to test the hypothesis about the applicability of machine learning methods to train models that allow to accurately predict the market capitalization of an enterprise based on data contained in three main forms of financial statements: Income statement, Balance sheet, and Cash flow statement.

The scientific novelty of the study lies in the proposal of an alternative approach to the actual finance problem —  business valuation.

The conducted empirical study allows us to test the hypothesis under consideration. We train various models using the most popular machine learning methods (LASSO, Elastic Net, KNN, Random Forest, SVM, and others). To determine the best approach for assessing the value of a company, the effectiveness of different methods is compared based on the R² performance metric (86,7% for the GBDT). Financial statements data of NYSE and NASDAQ companies are used. The study also addresses the problem of the interpretability of the trained models. The most important features are identified —  the forms of financial statements and their specific items that have the greatest impact on market capitalization. Three independent ways to determine feature importance indicate the significance of the information contained in the Income statement. In particular, Comprehensive income was the most important item for accurate predictions. Robust methods of variable normalization and missing data imputation are also highlighted. Finally, various ways of improving the developed models are recommended to achieve even higher accuracy of forecasts.

The study concludes that machine learning can be applied as a more accurate, unbiased, and less costly approach to value a company. Feature importance analysis can also be used to understand and further explore the value creation process.

1. Kryzanowski L., Galler M., Wright D. W. Using artificial neural networks to pick stocks. Financial Analysts Journal. 1993;49(4):21–27. DOI: 10.2469/faj.v49.n4.21

2. Cao L. AI in finance: A review. SSRN Electronic Journal. 2020. DOI: 10.2139/ssrn.3647625

3. Damodaran A. Investment valuation: Tools and techniques for determining the value of any asset. Hoboken, NJ: John Wiley & Sons, Inc.; 2012. 992 p.

4. Cybenko G. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems. 1989;2(4):303–314. DOI: 10.1007/BF02551274

5. Gu S., Kelly B., Xiu D. Empirical asset pricing via machine learning. The Review of Financial Studies. 2020;33(5):2223–2273. DOI: 10.1093/rfs/hhaa009

6. Tikhonov A. N. On the solution of ill-posed problems and the regularization method. Doklady Akademii nauk. 1963;151(3):501–504. URL: http://www.mathnet.ru/links/76d17d1b225aa6609693b033d8ad3c25/dan28329.pdf (In Russ.).

7. Tibshirani R. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological). 1996;58(1):267–288. DOI: 10.1111/J.2517–6161.1996.tb02080.x

8. Hindman M. Building better models: Prediction, replication, and machine learning in the social sciences. The Annals of the American Academy of Political and Social Science. 2015;659(1):48–62. DOI: 10.1177/0002716215570279

9. Carvalho D. V., Pereira E. M., Cardoso J. S. Machine learning interpretability: A survey on methods and metrics. Electronics. 2019;8(8):832. DOI: 10.3390/electronics8080832

10. Damodaran A. Valuation approaches and metrics: A survey of the theory and evidence. Hanover, MA: Now Publishers Inc.; 2007. 104 p.

11. Pinto J. E., Robinson T. R., Stowe J. D. Equity valuation: A survey of professional practice. Review of Financial Economics. 2019;37(2):219–233. DOI: 10.1002/rfe.1040

12. Böhm-Bawerk E. Recent literature on interest (1884–1899): A supplement to “Capital and interest”. New York: The MacMillan Co.; 1903. 151 p.

13. Atsalakis G. S., Valavanisb K. P. Surveying stock market forecasting techniques — Part II: Soft computing methods. Expert Systems with Applications. 2009;36(3):5932–5941. DOI: 10.1016/j.eswa.2008.07.006

14. Xing F. Z., Cambria E., Welsch R. E. Natural language based financial forecasting: A survey. Artificial Intelligence Review. 2018;50(1):49–73. DOI: 10.1007/s10462–017–9588–9

15. Park B., Bae J. K. Using machine learning algorithms for housing price prediction: The case of Fairfax County, Virginia housing data. Expert Systems with Applications. 2015;42(6):2928–2934. DOI: 10.1016/j.eswa.2014.11.040

16. Whitbeck V. S., Kisor M., Jr. A new tool in investment decision-making. Financial Analysts Journal. 1963;19(3):55–62. DOI: 10.2469/faj.v19.n3.55

17. Koklev P. S. Impact of the state ownership in equity on company value. Tendentsii razvitiya nauki i obrazovaniya. 2020;(60–8):14–18. (In Russ.). DOI: 10.18411/lj-04–2020–154

18. Joshi H., Chauha R. Determinants and prediction accuracy of price multiples for South East Asia: Conventional and machine learning analysis. Indonesian Capital Market Review. 2020;12(1):42–54. DOI: 10.21002/icmr.v12i1.12051

19. Liu J., Nissim D., Thomas J. Equity valuation using multiples. Journal of Accounting Research. 2002;40(1):135– 172. DOI: 10.1111/1475–679X.00042

20. Hastie T., Tibshirani R., Friedman J. The elements of statistical learning: Data mining, inference, and prediction. 2nd ed. New York: Springer-Verlag; 2016. 767 p. (Springer Series in Statistics). DOI: 10.1007/978–0–387–84858–7

21. Prokhorenkova L., Gusev G., Vorobev A., Dorogush A. V., Gulin A. CatBoost: Unbiased boosting with categorical features. In: Proc. 32nd Int. conf. on neural information processing systems (NIPS’18). (Montréal, December 3–8, 2018). New York: Curran Associates Inc.; 2018:6639–6649. URL: https://proceedings.neurips.cc/paper/2018/file/14491b756b3a51daac41c24863285549-Paper.pdf

22. Ioannidis J., Doucouliagos C. What’s to know about the credibility of empirical economics? Journal of Economic Surveys. 2013;27(5):997–1004. DOI: 10.1111/joes.12032

23. Bergstra J., Bengio Y. Random search for hyper-parameter optimization. Journal of Machine Learning Research. 2012;13(2):281–305. URL: https://www.jmlr.org/papers/volume13/bergstra12a/bergstra12a.pdf

24. Breiman L. Random forests. Machine Learning. 2001;45(1):5–32. DOI: 10.1023/A:1010933404324

25. Shapley L. S. A value for n-person games. In: Kuhn H. W., Tucker A. W., eds. Contributions to the theory of games. Vol. II. Princeton, NJ: Princeton University Press; 2016:307–318. DOI: 10.1515/9781400881970–018

26. Banko M., Brill E. Scaling to very very large corpora for natural language disambiguation. In: Proc. 39th Annu. meet. of the Association for Computational Linguistics (ACL’01). (Toulouse, July 06–11, 2001). Stroudsburg, PA: Association for Computational Linguistics; 2001:26–33. DOI: 10.3115/1073012.1073017

27. Buck S. F. A method of estimation of missing values in multivariate data suitable for use with an electronic computer. Journal of the Royal Statistical Society. Series B (Methodological). 1960;22(2):302–306. DOI: 10.1111/j.2517–6161.1960.tb00375.x

28. Munkhdalai L., Munkhdalai T, Namsrai O.-E., Lee J. Y., Ryu K. H. An empirical comparison of machine-learning methods on bank client credit assessments. Sustainability. 2019;11(3):699. DOI: 10.3390/su11030699

29. Huber P. J. Robust estimation of a location parameter. In: Kotz S., Johnson N. L., eds. Breakthroughs in statistics: Methodology and distribution. New York: Springer-Verlag; 1992:492–518. (Springer Series in Statistics). DOI: 10.1007/978–1–4612–4380–9_35

30. Sehrawat S. Learning word embeddings from 10-K fi lings for fi nancial NLP tasks. SSRN Electronic Journal. 2019. DOI: 10.2139/ssrn.3480902

31. Kovalev V. V., Drachevsky I. S. Dividend policy as a factor for managing company value: Comparing trends in emerging markets. Vestnik Sankt-Peterburgskogo universiteta. Ekonomika = St Petersburg University Journal of Economic Studies (SUJES). 2020;36(1):95–116. DOI: 10.21638/spbu05.2020.105

32. Abramishvili N. R., Lvova N. A., Voronova N. S. Is it possible to assess the corporate market value in the emerging market? In: New challenges of economic and business development — 2019: Incentives for sustainable economic growth. Proc. 11th Int. sci. conf. (Riga, May 16–18, 2019). Riga: University of Latvia; 2019:12–21. URL: https://dspace.lu.lv/dspace/handle/7/48896 (дата обращения: 18.12.2021).