A Neuro-Fuzzy Pricing Model in Conditions of Market Uncertainty
The article proposes a pricing model in the face of uncertainty at an early stage in the product life cycle. The development of new products, products, and design solutions is characterizing by the lack of the necessary amount of value and physical indicators for accurate pricing. At the early stage of the product life cycle, it is possible to operate only with its intended function or consumer properties. The number of statistical data on the demand for such a product on the market is severely limiting due to its novelty. Therefore, data on the results of sales of products with similar characteristics are taking as the initial statistical sample. The model is basing on expert assessment methods and the construction of hybrid neural networks. The analysis of the retrospective data is carried out taking into account the expert’s ideas about the features of the system. The simulation was performing in the MATLAB software environment with the Fuzzy Logic Toolbox expansion pack.
KeywordsPricing Hybrid neural networks Expert assessments Membership functions ANFIS editor Fuzzy inference
The reported study was funded by RFBR according to the research project No. 17-01-00817A.
- 1.Kovalev, A.P.: Modern trends in the development of the cost analysis methodology. Vestn. MGTU Stankin 4(35), 147–154 (2015)Google Scholar
- 2.Borodulin, A.N.: The use of neuro-fuzzy methods in the pricing system. Control Syst. Inf. Technol. 2(44), 53–57 (2011)Google Scholar
- 3.Terano, T., Asai, K., Sugeno, M.: Applied Fuzzy Systems: Translation from the Japanese Candidate Tech. Sciences of Chernyshov, Yu.N., Mir, M. 363 p (1993)Google Scholar
- 4.Kruglov, V.V.: Fuzzy Logic and Artificial Neural Networks, p. 224. Fizmatlit, Moscow (2001). Kruglov, V.V., Dly, M.I., Golunov, R.Yu.M.Google Scholar
- 5.Andrievskaya, N.V., Reznikov, A.S., Cheranev, A.A.: Features of the use of neuro-fuzzy models for the problems of the synthesis of automatic control systems. Fundam. Res. 7, 1445–1449 (2014). 11–7Google Scholar
- 6.MATLAB Fuzzy Logic Toolbox User’s Guide. The MathWorks, Inc. 333 p (2008)Google Scholar
- 9.Kaftannikov, I.L., Parasich, A.V.: Problems of formation of a training sample in machine learning tasks. Bull. S. Ural State Univ. Ser. Comput. Technol. Manag. Electron. 16(3), 15–42 (2016)Google Scholar
- 10.Leonenkov, A.V.: Fuzzy modeling in MATLAB and fuzzyTECH. SPb.: BHV-Petersburg, 736 p (2005)Google Scholar
- 11.Tarasyan, V.S.: Fuzzy Logic Toolbox for Matlab: Study Guide, p. 112. Publishing house of Ural State University of Railway Engineering, Yekaterinburg (2013)Google Scholar