Research article Special Issues

BOMD: Building Optimization Models from Data (Neural Networks based Approach)

  • Received: 27 July 2019 Accepted: 19 September 2019 Published: 30 September 2019
  • JEL Codes: C45, D22, D83, M11

  • This article aims to develop mathematical methods and algorithms that automatically build nonlinear models of planning and management of economic objects based on the use of empirical samples (observations). We call the relevant new information technology "Building Optimization Models from Data (BOMD)". The offered technology BOMD allows to obtain an objective control models that reflect the real economic processes. This is its main advantage over commonly employed subjective approach to management. To solve the problems posed in the article, the methods of artificial intelligence were used, in particular, the training of neural networks and construction of decision trees. If the learning sample contains simultaneously the values of the objective function and the values of characteristic function of constraints, it is proposed to use an approach based on the training of two neural networks: NN1 - for the synthesis of the objective function and NN2 - for the synthesis of the approximating characteristic function of constraints (instead of a neural network NN2, a decision tree can be used). The solution of the problem presented by such synthesized neural model may end up finding, generally speaking, a local conditional extremum. To find the global extremum of the multiextremal neural objective function, a heuristic algorithm based on a preliminary classification of the search area by using the decision tree is developed. Presented in the paper approach to an extraction of conditionally optimization model from the data for the case when there is no information on the points not belonging to the set of admissible solutions is fundamentally novel. In this case, a heuristic algorithm for approximating the region of admissible solutions based on the allocation of regular (non-random) empty segments of the search area is developed.

    Citation: Vladimir Donskoy. BOMD: Building Optimization Models from Data (Neural Networks based Approach)[J]. Quantitative Finance and Economics, 2019, 3(4): 608-623. doi: 10.3934/QFE.2019.4.608

    Related Papers:

  • This article aims to develop mathematical methods and algorithms that automatically build nonlinear models of planning and management of economic objects based on the use of empirical samples (observations). We call the relevant new information technology "Building Optimization Models from Data (BOMD)". The offered technology BOMD allows to obtain an objective control models that reflect the real economic processes. This is its main advantage over commonly employed subjective approach to management. To solve the problems posed in the article, the methods of artificial intelligence were used, in particular, the training of neural networks and construction of decision trees. If the learning sample contains simultaneously the values of the objective function and the values of characteristic function of constraints, it is proposed to use an approach based on the training of two neural networks: NN1 - for the synthesis of the objective function and NN2 - for the synthesis of the approximating characteristic function of constraints (instead of a neural network NN2, a decision tree can be used). The solution of the problem presented by such synthesized neural model may end up finding, generally speaking, a local conditional extremum. To find the global extremum of the multiextremal neural objective function, a heuristic algorithm based on a preliminary classification of the search area by using the decision tree is developed. Presented in the paper approach to an extraction of conditionally optimization model from the data for the case when there is no information on the points not belonging to the set of admissible solutions is fundamentally novel. In this case, a heuristic algorithm for approximating the region of admissible solutions based on the allocation of regular (non-random) empty segments of the search area is developed.


    加载中


    [1] Abiodun OI, Jantan A, Omolara AE, et al. (2018) State-of-the-art in artificial neural network applications: A survey. Heliyon 4: 1-7.
    [2] Antonova GM (2011) Application of Pattern Recognition Methods to Solve Optimization Problems Using Imitation Models. Pattern Recognit Image Anal 21: 113-116. doi: 10.1134/S1054661811020076
    [3] Barton D, Court D (2013) Three Keys to Building a Data-Driven Strategy. Available from:https://www.mckinsey.com/business-functions/digital-mckinsey/our-insights/three-keys-to-building-a-data-driven-strategy.
    [4] Boz O (2002) Converting A Trained Neural Network To a Decision Tree DecText - Decision Tree Extractor. ICMLA 2002: Las Vegas, Nevada, USA 4: 110-116.
    [5] Breiman L, Friedman JH, Olshen R, et al. (1984) Classification and Regression Trees, Chapman and Hal, New York, NY.
    [6] Corne D, Lones MA (2018) Evolutionary Algorithms, In: Marti R, Panos P, and Resende M. (eds) Handbook of Heuristics, Springer, Cham.
    [7] Donskoy VI (2018) A Synthesis of Pseudo-Boolean Empirical Models by Precedential Information. Bulletin of the South Ural State University, Series: Mathematical Modelling, Programming and Computer Software 11: 96-107.
    [8] Donskoy VI (2017) Extraction of Optimization Models from Data: a Decision Tree and Forest based Approach. Taurida J Comput Sci Theory Math 4: 59-86.
    [9] Donskoy VI (1993) Partially Defined Optimization Problems: An Approach to a Solution that is based on Pattern Recognition Theory. J Sov Math 65: 1664-1668. doi: 10.1007/BF01097516
    [10] Donskoy VI (2012) Synthesis of coordinated linear optimization models according to precedential information: an approach based on Kolmogorov complexity. Taurida J Comput Sci Theory Math 1:13-25.
    [11] El-Sawi AA, Hussein MA, Zaki EM, et al. (2014) An Introduction to Genetic Algorithms: A survey. A practical Issues. Int J Sci Eng Res 5: 252-262.
    [12] Eremin II, Mazurov VlD (1979) Unsteady processes of mathematical programming, Nauka, Moscow.
    [13] Haykin S (2008) Neural Networks and Learning Machines, Prentice Hall.
    [14] Hornik K, Stinchcombe M, White H (1990) Univrsal Approximation of an Unknown Mapping and Derivatives Using Multilayer Feedforward Networks. Newral Networks 3: 551-560. doi: 10.1016/0893-6080(90)90005-6
    [15] Kolmogorov AN (1991) Algorithm, information, complexity, Znanie, Moscow.
    [16] Loh WY (2014) Fifty Years of Classification and Regression Trees. Int Stat Rev 82: 329-348. doi: 10.1111/insr.12016
    [17] MathWorks (2017) Building Models from Data and Scientific Principles. Available from: https://www.mathworks.com/solutions/mathematical-modeling/building-models-data-scientificprinciples.html.
    [18] Mazurov VlD (1971) Application of Methods of Theory of Pattern Recognition in the Optimal Planning and Management. Proceeding of I-st all-Union Conference on Optimal Planning and National Economy Management. Moscow.
    [19] Malhotra R, Singh N, Singh Y (2011) Genetic Algorithms: Concepts, Design for Optimization of Process Controllers. Comput Inf Sci 4: 39-54.
    [20] Roh Y, Heo G, Whang SE (2019) A Survey on Data Collection for Machine Learning. ArXiv: 1811.03402v2(201 [cs.LG].
    [21] Zhang S, Zhang C, Yang Q (2003) Data Preparation for Data Mining. Appl Artif Intell 17: 375-381. doi: 10.1080/713827180
  • Reader Comments
  • © 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(2951) PDF downloads(404) Cited by(7)

Article outline

Figures and Tables

Figures(6)  /  Tables(1)

Other Articles By Authors

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog