The advantages of neural network technology is shown in comparison of traditional descriptions of dynamically changing systems, which include a modern land market. The basic difficulty arising in the practical implementation of neural network models of the land market and construction products is revealed It is the formation of a representative set of training and test examples. The requirements which are necessary for the correct description of the current economic situation has been determined, it consists in the fact that Train-paid-set in the feature space should not has the ranges with a low density of observations. The methods of optimization of empirical array, which allow to avoid the long-range extrapolation of data from range of concentration of the set of examples are formulated. It is shown that a radical method of optimization a set of training and test examples enclosing to collect supplemantary information, is associated with significant costs time and resources for the economic problems and the ratio of cost / efficiency is less efficient than an algorithm optimization neural network models the earth market fixed set of empirical data. Algorithm of optimization based on the transformation of arrays of information which represents the expansion of the ranges of concentration of the set of examples and compression the ranges of low density of observations is analyzed in details. The significant reduction in the relative error of land price description is demonstrated on the specific example of Voronezh region market of lands which intend for road construction, it makes the using of radical method of empirical optimization of the array costeffective with accounting the significant absolute value of the land. The high economic efficiency of the proposed algorithms is demonstrated.

land market, road construction, neural network, optimization, economic efficiency

1. Greshilov A.A. Matematicheskie metody prinyatiia reshenii [Mathematical methods of decision-making] Мoscow, MGTU im. N.E. Baumana, 2006. 583 p. (in Russian)

2. Stanley J. Introduction to Neural Networks. Sierra Madre, CA. California Scientific Software, 2011, 311 p.

3. Hinton G.E., Sejnowski. T.J. Learning and Relearning in Boltzmann Machines». P-rullel Distributed Proceedings, 1996, vol. 11, pp. 282–317.

4. Tsypkin A.I. Neironnye seti: Istoriia razvitiia teori [Neural Networks: Theory of History] Moscow, IPRZhR, 2011, 517 p. (in Russian)

5. Bir S. Mozg firmy [Firms brain] Мoscow, Radio i sviaz’, 1993. 524 p. (in Russian)

6. Eldon Y. L., San-Hsing, Ming-Hsiung, Chia-Yi Applications Artificial neural networks and their business applications. Information & Management. Institute of Information Management, National Chung Cheng University of Taiwan, R.O.C., 2014, pp. 303–313.

7. Frolov Yu.V., Pastukhov E.S. Monitoring changes in the Russian banking community with the use of self-organizing maps of Kohonen. Bankovskie tekhnologii [Banking technologies] 2012, no. 11. (in Russian)

8. Nedosekin A.O., Zabolotskiy S.N. The approach to recording debt stock management programs. Audit i finansovyi analiz [Audit and Financial Analysis] 2001, no. 1, 31 p. (in Russian)

9. Karpovich M.A. Neural network methods of estimating costs for scientific research, design and development works Vestnik Voronezhskogo gosudarstvennogo universiteta inzhenernykh tekhnologiy [Proceedings of VSUET] 2014, no.1, pp. 235–240. (In Russian)

10. Galushkin A. I. Primenenie neirokomputerov v finansovoi deiatelnosti [Applications of neuro-computers in financial activities] Novosibirsk, Nauka, 2002, 215p. (in Russian)

11. Barron A.R. Predicted Squarer Errors: A Criterion for Automatic Model Selection. New York: Marcel Dekker, 2006. 311 p.