The study of the relationship between stock value and financial performance of iron and steel enterprises using artificial intelligence techniques

Abstract

Study of the relationship between finance performance and market equity value of Russian public companies, such as PJSC Mechel, PJSC Novolipetsk Iron and Steel Works, PJSC Magnitogorsk Iron and Steel Works, PJSC Severstal using the artificial neural network (ANN) has been carried out. Data of annual financial statements, stock-exchange equity prices, USD/RUB, EUR/USD exchange rates, RF CB base rate were used as initial data. The number of instructional examples was equal to 15 and there were 16 input values included into each example. In the end, ANN calculated the ratio of the market value of one share to equity capital per share. ANN training was carried out using the backpropagation method and the conjugate gradient method. The average values of discrepancies between the actual value of the ratio of market value to equity capital and calculated value using ANN were 6.0, 2.5, 8.2 % for NLMK, Severstal and MMK, respectively. The use of ANN has shown the overestimated value of equity stock-exchange quotations of PJSC Mechel in relation to the market averages.