Neural Networks Method in modeling of the financial company’s performance

The content of modern management accounting is formed in conjunction with the rapid development of information technology, using complex algorithms of economic analysis. It makes possible the practical realization of the effective management idea - management of key performance indicators, which certainly includes the indicators of financial performance of economic entities.

An important place in this process is given to the construction and calculation of factorial systems of economic indicators. A substantial theoretical and empirical experience has been accumulated to solve the problems that arise. The aim of this study is to develop a universal modern model for factor analysis of finance results, allowing multivariate solutions both current and promising character with monitoring in real time.

The realization of this goal is achievable by using artificial neural networks (ANN) in an appropriate simulation, which are increasingly used in the economy as a tool for supporting management decisionmaking. In comparison with classical deterministic and stochastic models, ANN brings the intellectual component to the modeling process. They are able to learn to function based on the gained experience, the result of allowing less and less mistakes.

The article reveals the advantages of such an alternative approach. An alternative approach to factor analysis, based on the method of neural networks, is proposed. Advantages of this approach are marked. The paper presents a phased algorithm of modeling complex cause-and-effect nature relationships, including factors’ selection for the studied result, the creation of the neural network architecture and its training. The universality of such modeling lies in the fact that it can be used for any resulting indicator.

The authors have proposed and described a mathematical model of the factor analysis for financial indicators. It is important that the model included the factors of both direct and indirect actions with a range of quantitative parameters: conditional-ideal, real, the worst. The copyright factor selection algorithm complements the developed model. Because of the functioning of the neural network, a management report on the financial performance of the company is formed. During the research, the following methods have been used: the system approach in factors’ classification of financial results, factor analysis and mathematical modeling at development of the corresponding neural model. The research is based on a complex of theoretical and empirical developments of domestic and foreign authors. The actual digital materials of the real economic entity are involved in the verification phase of the research results.

The advantage of the model is the ability to track changes in the input data and indicators in the online mode, to build quality forecasts for future periods with different combinations of the whole set of factors. The proposed instrument of factor analysis has been tested in the activities of real companies. The factors can ensure growth in terms of financial results; visualization of business processes is enhanced, as well as the probability of making rational management decisions. 

1. Bulyga R.P., Mel’nik M.V. Audit biznesa. Ed. R.P. Bulygi. Moscow: YuNITI-DANA, 2013. 263 p. (In Russ.)

2. Kazakova K.A. Modelirovanie bankovskogo rezerva na pokrytie kreditnykh poter’: aspekt panel’nykh dannykh. Finansy i kredit. 2015. No. 21 (645). P. 44–56. (In Russ.)

3. Plaskova N.S. Stokhasticheskoe modelirovanie i otsenka rezul’tativnosti deyatel’nosti kommercheskoy organizatsii. Upravlencheskiy uchet. 2014. No. 7. P. 59–67. (In Russ.)

4. Frensis Gal’ton. Nasledstvennost’ talanta: Zakony i posledstviya. Moscow: Mysl’, 1996. 269 p. (In Russ.)

5. Steven B. Caudill, Fernando C. Zanella, Franklin G. Mixon. Is Economic Freedom One Dimensional? A Factor Analysis of Some Common Measures of Economic Freedom. Journal of economic development. 2000. No. 1. Volume 25.

6. Adamov V.E. Faktornyy indeksnyy analiz (Metodika i problemy). Moscow: Statistika, 1977. 200 p. (In Russ.)

7. Barilenko V.I. Biznes-analiz kak osnova upravleniya ustoychivym razvitiem korporatsiy. Menedzhment i biznes-administrirovanie. 2014. No. 4. P. 130–135. (In Russ.)

8. Fomin V.P. Fomin P.V. Analiticheskaya sostavlyayushchaya uspeshnogo upravleniya finansovymi rezul’tatami (kontseptual’nyy aspekt). Ekonomicheskiy analiz: teoriya i praktika. 2015. No. 31. P. 13–25. (In Russ.)

9. Fomin V.P. Fomin P.V. Analiticheskaya sostavlyayushchaya uspeshnogo upravleniya finansovymi rezul’tatami (prakticheskiy aspekt). Ekonomicheskiy analiz: teoriya i praktika. 2015. No. 36. P. 12–26. (In Russ.)

10. Sheremet A.D., Negashev E.V. Metodika finansovogo analiza deyatel’nosti kommercheskikh organizatsiy. Moscow: INFRA-M, 2008. 208 p. (In Russ.)

11. Mak-Kallok U.S., Pitts V. Logicheskoe ischislenie idey, otnosyashchikhsya k nervnoy aktivnosti. Avtomaty. Ed. K. E. Shennona i Dzh. Makkarti. Moscow: Izd-vo inostr. lit., 1956. P. 363– 384. (Translated in 1943). (In Russ.)

12. Nikiforova N.A., Dontsov E.V. Primenenie neyrosetevogo modelirovaniya dlya prognozirovaniya finansovogo sostoyaniya predpriyatiya. Upravlencheskiy uchet. 2011. No. 4. P. 36–46. (In Russ.)

13. Romanovskiy A.V. O primenenii iskusstvennykh neyronnykh setey dlya prognozirovaniya finansovykh pokazateley predpriyatiya. Audit i finansovyy analiz. 2013. No. 2. P. 363–370. (In Russ.)

14. Kurochkina I., Shuvalova E., Mamatova L., Kalinin I. Analysis model of the company’s financial performance based on neural network. In: 3rd International multidisciplinary scientific conference on social science & arts SGEM 2016, Conference Proceedings. Bulgaria: STEF 92 Technology Ltd. 2016. Book 2. Volume 111. pp. 49-57, DOI:10.5593/ sgemsocial2016B23

15. Khaykin Saymon. Neyronnye seti: polnyy kurs. 2nd ed. Translated from Eng. Moscow: Izdatel’skiy dom «Vil’yams», 2006. 1104 p. (In Russ.)

16. Moscow Tim Dzhons. Programmirovanie iskusstvennogo intellekta v prilozheniyakh. Per. s angl. Osipov A. I. Moscow: DMKPress, 2011. 312 p. (In Russ.)

17. Doklad RSPP «O sostoyanii delovogo klimata v Rossii v 2016 godu». URL: http://media. rspp.ru/document/1/f/9/f9c2ca5f8cd104f8d5d- 40f2a7b50fced.pdf (In Russ.)

18. Anita Bai, Swati Hira, P. P. Deshpande. An Application of Factor Analysis in the Evaluation of Country Economic Rank. ProcediaComputerScience. 2015. No. 54. pp. 311–317, DOI: 10.1016/j.procs.2015.06.036.

19. Darda E.S., Ustinov E.A. Faktory razvitiya fondovogo rynka Rossiyskoy Federatsii: statisticheskaya otsenka. Innovatsii i investitsii. 2016. No. 10. P. 70–78. (In Russ.)

20. Myl’nikov A.A. Metody issledovaniya struktury statisticheskoy informatsii v ASGS: dis. kand. ek. nauk: 08.00.13. Moscow, 1984. 181 P. (In Russ.)

21. Fal’ko S.G. Kontrolling dlya rukovoditeley i spetsialistov. Finansy i statistika. 2008. 272 p. (In Russ.)