Krichevskiy M.L., Martynova Yu.A.Published in:
Creative Economy
– Volume 12, Number 8 (August 2018)

JEL classification: D81, С45, С65

Keywords: artificial intelligence, efficiency evaluation, investment project, neuro-fuzzy system


Share:

Abstract:

The results of the analysis of the investment project with the help of a neuro-fuzzy system are presented. Unlike the traditional methods of evaluating the effectiveness of the project, which works poorly in conditions of incomplete information, it is proposed to use tools related to "weak" methods of artificial intelligence. As an instrument for solving the problem, an artificial neural network and a fuzzy logic system were chosen. Incorporation these technologies into a hybrid neuron-fuzzy system that combines the best properties of these methods has made it possible to form a quantitative assessment of the effectiveness of investment projects. The work of a neuron-fuzzy system of the type ANFIS (adaptive neuro-fuzzy inference system), implemented in the MatLab R2012b software package, is demonstrated. The regression equation connecting the input parameters of the investment project with the evaluation of its efficiency was derived and a comparison of the two approaches to the solution of the problem was made.

---

References:
Bulgakova L.N., Litovka G.L. (2014). Metodicheskie aspekty otsenki effektivnosti investitsionnyh proektov [Methodical aspects of estimation of efficiency of investment projects]. Management of economic systems. (10(70)). 1. (in Russian).
Coppin B. Artificial intelligence illuminated. SudburyJones & Bartlett Publishers. Retrieved from https://www.abebooks.com/9780763732301/Artificial-Intelligence-Illuminated-Jones-Bartlett-0763732303/plp
Doskočil R. (2016). An evaluation of total project risk based on fuzzy logic. Verslas: Teorija ir praktika Business: Theory and Practice. 17 (1). 23-31. doi: 10.3846/btp.2015.534.
Gracheva M.V., Sekerin A.B. (2009). Risk-menedzhment investitsionnogo proekta [Investment project risk management] Moscow: YuNITI-DANA. (in Russian).
Ingle M.M. (2017). Risk Analysis and Fuzzy Logic Based Project Evaluation Imperial Journal of Interdisciplinary Research. 3 (6). 107-111.
Jang J-S. R., Sun C-T., Mizutani E. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine IntelligencePrentice-Hall. Retrieved from https://www.dca.ufrn.br/~meneghet/FTP/anfis%2093.pdf
Jang R. (193). ANFIS :Adaptive-Network-Based Fuzzy Inference System IEEE Transactions on Systems, MAN, and Cybernetics. 23 (3). 665-685.
Kecman V. Learning and Soft Computing - Support Vector Machines, Neural Networks, and Fuzzy Logic Models. Retrieved from https://mitpress.mit.edu/books/learning-and-soft-computing
Krichevskiy M.L. (2018). Prikladnye zadachi menedzhmenta [Applied tasks of management] Moscow: Kreativnaya ekonomika. (in Russian).
Mousavi J., Ponnambalam K., Karray F. (2007). Inferring operating rules for reservoir operations using fuzzy regression and ANFIS Fuzzy Sets and Systems. 158 1064–1082.
Orekhova A.S.. Sokolov M.A. (2012). Otsenka effektivnosti investitsionnyh proektov i vybor optimalnogo puti razvitiya predpriyatiya [Assessment of investment projects efficiency and choice of an optimum way of the enterprisedevelopment]. Transport business in Russia. (6). 53-57. (in Russian).
Puryaev A., Puryaeva Zh., Mammaev R., Borisova L. (2015). Neural Networks in an Assessment of Investment Projects Efficiency Ayer. (4). 6-10.
Russell S., Norvig P. (2010). Artificial Intelligence: A Modern Approach Boston: Prentice Hall.
Методические рекомендации по оценке эффективности инвестиционных проектовNiec.ru. (in Russian). Retrieved from http://www.niec.ru/Met/02redMR.pdf
Рутковский Л. Методы и технологии искусственного интеллектаГорячая линия - Телеком. (in Russian). Retrieved from http://www.techbook.ru/book.php?id_book=400
Штовба С.Д. Проектирование нечетких систем средствами MATLABГорячая линия - Телеком. (in Russian). Retrieved from https://www.ozon.ru/context/detail/id/3179905