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.
Highlights
The use of artificial neural networks (ANNs) is especially reasonable in case when the studied value depends on myriad of factors and this dependence is implicit and stochastic
2.Problem statement and initial data This paper aims at assessment of the market value of companies PJSC Mechel (Mechel) and JSC ‘EVRAZ Nizhniy Tagil Iron and Steel Works’ (NTMK) using ANN based on annual statement data as well as assessment of the market value of companies PJSC Novolipetsk Iron and Steel Works (NLKM), PJSC Magnitogorsk Iron and Steel Works (MMK), PJSC Severstal (Severstal)
It should be noted that NTMK shares are not listed at stock exchanges; calculation of its market value can be carried out through the involvement of ANN trained according to the analogue companies
Summary
The use of artificial neural networks (ANNs) is especially reasonable in case when the studied value depends on myriad of factors and this dependence is implicit and stochastic. This is often demonstrated when studying financial and economic phenomena. The paper [1] considers the possibility of using ANN and semantic analysis to predict the corporate bankruptcy based on its annual financial statements. A neural network model was used in papers [5,6,7] to predict stock value, stock market trends, and relationships with technical analysis using Japanese candlesticks
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IOP Conference Series: Materials Science and Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
