Economic analysis of risky projects by ANNs


Taskin A., Guneri A. F.

APPLIED MATHEMATICS AND COMPUTATION, cilt.175, sa.1, ss.171-181, 2006 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 175 Sayı: 1
  • Basım Tarihi: 2006
  • Doi Numarası: 10.1016/j.amc.2005.07.016
  • Dergi Adı: APPLIED MATHEMATICS AND COMPUTATION
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.171-181
  • Yıldız Teknik Üniversitesi Adresli: Hayır

Özet

Multilayer perceptron (MLP) and radial basis function (RBF) artificial neural networks (ANN) are used to model economic analysis of risky projects and are presented in this paper. Analytical models of risky projects are investigated and neural network function approximation results are compared. A general, problem independent ANNs are developed for the normalized input values for risky projects. The expected cost value and variance are the outputs of the ANNs. The simulation results of RBF and MLP with respect to a mathematical model are shown and concluded. (c) 2005 Elsevier Inc. All rights reserved.