Neural network as a simulation metamodel in economic analysis of risky projects

An artificial neural network (ANN) model for economic analysis of risky projects is presented in this paper. Outputs of conventional simulation models are used as neural network training inputs. The neural network model is then used to predict the potential returns from an investment project having stochastic parameters. The nondeterministic aspects of the project include the initial investment, the magnitude of the rate of return, and the investment period. Backpropagation method is used in the neural network modeling. Sigmoid and hyperbolic tangent functions are used in the learning aspect of the system. Analysis of the outputs of the neural network model indicates that more predictive capability can be achieved by coupling conventional simulation with neural network approaches. The trained network was able to predict simulation output based on the input values with very good accuracy for conditions not in its training set. This allowed an analysis of the future performance of the investment project without having to run additional expensive and time-consuming simulation experiments.

[1]  James C. T. Mao,et al.  INVESTMENT DECISION UNDER UNCERTAINTY: THEORY AND PRACTICE , 1969 .

[2]  Paul A. Luker,et al.  Qualitative Simulation Modeling and Analysis , 1991, Advances in Simulation.

[3]  Robert W. Blanning,et al.  The construction and implementation of metamodels , 1975 .

[4]  Adedeji Badiru,et al.  An artificial neural network case study: prediction versus classification in a manufacturing application , 1993 .

[5]  A. Alan B. Pritsker,et al.  Slam II network models for decision support , 1989 .

[6]  Salah E. Elmaghraby,et al.  Project bidding under deterministic and probabilistic activity durations , 1990 .

[7]  Jack P. C. Kleijnen,et al.  Regression metamodels for generalizing simulation results. , 1979 .

[8]  J. Stephen Judd,et al.  Neural network design and the complexity of learning , 1990, Neural network modeling and connectionism.

[9]  Hershey H. Friedman,et al.  Validating the simulation metamodel: Some practical approaches , 1985 .

[10]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[11]  J. Kleijnen.  Statistical tools for simulation practitioners , 1986 .

[12]  Abraham Mehrez,et al.  The meta-model of OR/MS , 1989 .

[13]  F. Choobineh,et al.  Use of Intervals and Possibility Distributions in Economic Analysis , 1992 .

[14]  Charles Leave.  Neural Networks: Algorithms, Applications and Programming Techniques , 1992 .

[15]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[16]  Christian N. Madu.  Simulation in manufacturing: A regression metamodel approach , 1990 .

[17]  Joseph Sarkis,et al.  A metamodel-based decision support system for shop floor production control , 1992 .

[18]  Li Lin,et al.  Metamodels of production line transient behaviour for sudden machine breakdowns , 1990 .

[19]  Chan S. Park,et al.  Advanced engineering economics , 1990 .

[20]  James R. Wilson,et al.  Estimation of multiresponse simulation metamodels using control variates , 1989 .

[21]  M. A. Mustafa,et al.  Project risk assessment using the analytic hierarchy process , 1991 .

[22]  J. D. Tew.  Correlation-induction techniques for fitting second-order metamodels in simulation experiments , 1989, WSC '89.

[23]  Jack Hirshleifer,et al.  Investment Decision under Uncertainty: Choice—Theoretic Approaches , 1965 .

[24]  B. Blanchard,et al.  Life-cycle cost and economic analysis , 1991 .

[25]  Lee W. Schruben,et al.  An experimental procedure for simulation response surface model identification , 1987, CACM.

[26]  S. Andrew Starbird.  A Metamodel Specification for a Tomato Processing Plant , 1990 .

[27]  Larry Williams,et al.  An Application of Simulation and Network Analysis to Capacity Planning and Material Handling Systems at Tinker Air Force Base , 1989 .

[28]  Averill M. Law,et al.  Simulation Modeling and Analysis , 1982 .

[29]  Enver Yücesan,et al.  Proceedings of the 1989 winter simulation conference , 1989 .

[30]  O. J. Vrieze,et al.  Metamodelling and experimental design: Case study of the greenhouse effect , 1990 .

[31]  Colin M. Sorrill.  Risk Analysis for Large Projects: Models, Methods and Cases , 1987 .

[32]  S. Andrew Starbird.  The identification of significant terms in a flexible metamodel using spectral analysis , 1991 .

[33]  Adedeji B. Badiru.  A simulation approach to PERT network analysis , 1991, Simul..

[34]  Linda Weiser Friedman.  Establishing functional relationships in multiple response simulation: The multivariate general linear metamodel , 1984, WSC '84.

[35]  R. M. Skitmore,et al.  Project management under uncertainty , 1989 .

[36]  R. D. Hurrion,et al.  Using a Neural Network to Enhance the Decision Making Quality of a Visual Interactive Simulation Model , 1992 .

[37]  George J. Klir,et al.  Aspects of uncertainty in qualitative systems modeling , 1991 .

[38]  Adedeji Badiru,et al.  Expert Systems Applications in Engineering and Manufacturing , 1998 .