Forecasting of influence of the external environment risks on financial independence of an industrial airline company

Economic Annals-XXI: Volume 129, Issue 5-6(1), Pages: 79-81

Citation information:
Piletska, S. (2013). Forecasting of influence of the external environment risks on financial independence of an industrial airline company. Economic Annals-XXI, 5-6(1), 79-81. https://ea21journal.world/index.php/ea-v129-21/

Samira Piletska
PhD (Economics),
Associate Professor,
Doctoral Candidate,
National Aviation University, Kyiv, Ukraine
samirapiletskaya@mail.ru

Forecasting of influence of the external environment risks on financial independence of an industrial airline company

Abstract. In recent years, Ukrainian enterprises of aviation industry operate with shortage of financial resources to meet the needs of not only economic development, but their operational activity. Difficult financial situation caused by the negative impact of external environmental factors has led to structural imbalances in the system of expanded reproduction, reduced competitiveness in domestic and foreign markets, as well as investment activity. The above circumstances indicate the need for a strategy of financial independence, which would be directed at predicting and minimizing risks exposure in the environment.

To assess the strategic potential of achieving financial independence of industrial airline company the Balanced Scorecard System is offered. To predict the impact of environmental risks on the value of an airline company’s strategic potential to achieve financial independence, a multilayer neural network model is used. The algorithm is as follows: preparation of input and output data for the neural network, establishment a logical connection between them, creation, initialization and network modeling, adaptation and study; checking network for data not involved in study; evaluating the significance of predictions. The input variables are the risk levels of the environment. The layers achieved are key performance indicators for each component of the balanced scorecard system: internal business processes, financing, educating and development of staff; clientele. The process of radial basis function of neural network study consists of two stages: setup process of basis functions’ centres and training of neurons in the hidden layer. To realize a neural network with multiple outputs following types are preferred: multilayer perceptron neural network and RBF network.

MAPE index for the two implemented neural networks is defined and on the basis of this index the most appropriate and high quality one for the approximation of neural networks is selected. It is proved that multilayer perceptron usage for prediction of parameters would provide high quality predictions. On the assumption of such prediction it becomes possible to further improve the quality of the enterprise’s equity and debt formation and management of its structure. All calculations are performed by the author using the package «Statistica Neural Networks».

Keywords: Financial Independence; External Environment; Risk; Strategy; Strategic Potential; Neural Network

JEL Classification: D21; C45; C53

References

1. Ansoff, I. (1989). Strategic Management (Trans. for Engl.). Moscow: Economics (in Russ.).
2. Kaplan, R. S., & Norton, D. (2005). The Balanced Scorecard From the strategy to action (Trans. for Engl.). Moscow: Olympus-Business (in Russ.).
3. Markova, V. D., & Kuznetsova, S. A. (2000). The Strategic Management. Moscow: INFRA-M (in Russ.).
4. Vitlinskyi, V. V., & Velykoivanenko, P. I. (2004). The risk management in the economy and entrepreneurship. Kyiv: MBK (in Ukr.).
5. Vnukova, N. M., & Smolyak, V. A. (2002). The basic method of the economic risk assessing of the enterprises. Finances of Ukraine, 10, 15-21 (in Ukr.).
6. Podolchak, N. (2002). Risks classification and the methods of reducing. Herald of the National University «Lviv Polytechnic», 417, 531-537 (in Ukr.).
7. Raizberg, B., Lozovskyi, L., & Starodubtseva, E. (n.d.). The economic mechanism.
   Retrieved from http://www.smartcat.ru/Referat/atyelramnz.shtml (in Russ.)
8. Kalinin, I. O. (2009). The study of neural network techiques in prediction problems.
   Retrieved from http://www.nbuv.gov.ua/portal/Soc_Gum/Npchdu/Computer_technology/2009_93/93-17.pdf
9. Kizim, N. A., Yastremskaya, E. N., & Senchukova, V. F. (2006). The neural networks: theory and practice. Kharkov: INZHEK (in Russ.).
10. Meshcheryakov, V. A. (2004). The construction machinery’s identification as non-linear dynamic systems based on neural network technology. Paper presented at II Russian Conference «Design engineering and scientific applications in MATLAB» (pp. 1300-1308). Moscow: Institute of Control Science V. A. Trapeznikov RAS (in Russ.).
11. Haykin, S. (2006). The neural networks: a complete course (2^nd ed.). Moscow: William (in Russ.).

Received 04.04.2013