ECONOMIC VALUATION OF CAPITAL PROJECTS USING NEURAL NETWORK METAMODELS

ABSTRACT It is often useful to incorporate a metamodel into the sensitivity analysis of the economics of capital projects. While statistical models are straightforward and understandable, they are not always appropriate, especially where there are discontinuities or complex relationships in the economic data. This paper puts forth a neural network approach that uses design of experiments to generate metamodel training and validation data from the project(s) under consideration. Both backpropagation multi-layered perceptron networks and cascade correlation networks are explored and compared with the statistical approach. It is shown that the backpropagation networks work well for a variety of data sets and can be superior to regression in prediction accuracy when the economic data is especially complicated.

[1]  Alice E. Smith,et al.  A METAMODEL APPROACH TO SENSITIVITY ANALYSIS OF CAPITAL PROJECT VALUATION , 1997 .

[2]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[3]  Willem J. H. Van Groenendaal,et al.  Estimating NPV variability for deterministic models , 1998, Eur. J. Oper. Res..

[4]  Christian N. Madu,et al.  Polynomial metamodelling and Taguchi designs in simulation with application to the maintenance float system , 1994 .

[5]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[6]  Adedeji B. Badiru,et al.  Neural network as a simulation metamodel in economic analysis of risky projects , 1998, Eur. J. Oper. Res..

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[8]  Alice E. Smith,et al.  Bias and variance of validation methods for function approximation neural networks under conditions of sparse data , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[9]  B. Yu,et al.  Metamodels in manufacturing: a review , 1994 .

[10]  Ted Eschenbach.  Cases in engineering economy , 1989 .

[11]  Benjamin W. Wah,et al.  Automated learning for reducing the configuration of a feedforward neural network , 1996, IEEE Trans. Neural Networks.

[12]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

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

[14]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[15]  W. G. Sullivan,et al.  Capital Investment Analysis For Engineering And Management , 1995 .

[16]  Michael J. Drevna,et al.  A Simulation Metamodel for Response‐Time Planning* , 1998 .

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

[18]  R. D. Hurrion,et al.  An example of simulation optimisation using a neural network metamodel: finding the optimum number of kanbans in a manufacturing system , 1997 .

[19]  Russell R. Barton,et al.  Metamodels for simulation input-output relations , 1992, WSC '92.

[20]  Jack P. C. Kleijnen,et al.  A methodology for fitting and validating metamodels in simulation , 2000, Eur. J. Oper. Res..

[21]  Ted G. Eschenbach,et al.  Exposition on Using Graphs for Sensitivity Analysis , 1989 .

[22]  Larry J. Shuman,et al.  Computing confidence intervals for stochastic simulation using neural network metamodels , 1999 .

[23]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[24]  Donald S. Remer,et al.  Buying a Home Versus Renting an Apartment: A Case Study , 1990 .