Published in «Russian Journal of Innovation Economics»3 / 2019
DOI: 10.18334/vinec.9.3.41177

Selection finance's source by method of machine learning

Martynova Yuliya Anatolevna, Saint-Petersburg State University of Aerospace Instrumentation (SUAI), Russia

Выбор источника финансирования методами машинного обучения - View in Russian

 Download PDF | Downoads: 19

Abstract:
The results of choosing a financial institution for servicing organizations using the technologies used in machine learning, in particular, neural networks and fuzzy logic, are presented. In the conditions of insufficient information, traditional methods of solving such tasks do not work reliably enough, therefore, the work demonstrates a method for determining the best bank using these technologies. To search for the desired solution, the simulation of random values of those parameters that are responsible, in the opinion of the author, for the choice of a bank, was performed. Such a database of examples, which can be called “toy“ is involved in the training of the neural network. In addition, it is shown the possibility of obtaining an assessment of the effectiveness of the selected institution for servicing the organization using fuzzy logic.

Keywords:

fuzzy logic, machine learning, neural network, performance evaluation

JEL-Classification: D81, С45, С65

Citation:
Martynova Yu.A. (2019). Selection finance's source by method of machine learning [Vybor istochnika finansirovaniya metodami mashinnogo obucheniya]. Russian Journal of Innovation Economics, 9(3). (in Russian). – doi: 10.18334/vinec.9.3.41177.


References (transliterated):
Alpaydın E. (2010). Introduction to Machine Learning Massachusetts: MIT Press Cambridge.
Fuzzy Logic Toolbox. MatLabMathworks. Retrieved May 12, 19, from https://www.mathworks.com/products/fuzzy-logic.html?BB=1
Krichevskiy M.L., Dmitrieva S.V., Martynova Yu.A. (2018). Neyrosetevaya otsenka kompetentsiy personala [Neural network assessment of personnel competencies]. Russian Journal of Labor Economics. 5 (4). 1101-1118. (in Russian). doi: 10.18334/et.5.4.39488.
Krichevskiy M.L., Martynova Yu.A. (2018). Instrumenty iskusstvennogo intellekta pri otsenke effektivnosti investitsionnogo proekta [Instruments of artificial intelligence in assessment of effectiveness of investment project]. Creative economy. 12 (8). 1105-1118. (in Russian). doi: 10.18334/ce.12.8.39265.
Nielsen M. Neural Networks and Deep Learning. Retrieved April 12, 2019, from http://neuralnetworksanddeeplearning.com
Principal Component AnalysisAcadgild. Retrieved May 19, 2019, from https://acadgild.com/blog/principal-component-analysis
Ramsundar B., Zade R. (2019). TensorFlow dlya glubokogo obucheniya [TensorFlow for deep learning] SPb.: BKhV-Peterburg. (in Russian).
Shakla N. (2019). Mashinnoe obuchenie i TensorFlow [Machine learning and TensorFlow] SPb.: Piter. (in Russian).
Shalev-Shwartz S., Ben-David S. (2014). Understanding Machine Learning: From Theory to Algorithms New York: Cambridge University Press.