Neural networks versus parameter-based applications in cost estimating

Abstract

Cost estimating is essentially a computational process that attempts to predict the final cost of a future project, even though not all of the parameters and conditions are known when the cost estimate is prepared. In general, estimating methods vary considerably, depending upon the available information, the nature of the project, and the time available to prepare the estimate. In this article, we discuss some recent applications of parametric estimating in analyzing cost data and making predictions. We also investigate the potential application of neural networks to estimating problems. Both of these methodologies use a parameter-based approach in modeling cost. However, the computational techniques used to analyze cost data and produce results are significantly different. As an illustration, we provide a numerical example that may be used to compare the performance of parametric estimating and neural networks. 8 refs., 3 figs., 3 tabs.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 39 citations exist upstream.