Cost estimation predictive modeling: regression versus neural network.

From: Engineering Economist | Date: January 1, 1997| Author: | Copyright information

Cost estimation generally involves predicting labor, material, utilities or other costs over time given a small subset of factual data on "cost drivers." Statistical models, usually of the regression form, have assisted with this projection. Artificial neural networks are non-parametric statistical estimators, and thus have potential for use in cost estimation modeling. This research examined the performance, stability and ease of cost estimation modeling using regression versus neural networks to develop cost estimating relationships (CERs). Results show that neural networks have advantages ...

Read all of this article with a FREE trial to HighBeam Research

Related newspaper, magazine, and trade journal articles from HighBeam Research

(Including press releases, facts, information, and biographies)

Cost estimation predictive modeling: Regression versus neural network
; ...and ease of cost estimation modeling...regression versus neural networks to develop...artificial neural networks, to the field of cost estimation. Applying...the use of neural networks for cost estimation is the research...
Understanding neural networks as statistical tools.
; 1. INTRODUCTION Neural networks have recently received a great...From a statistical perspective neural networks are interesting because of their...and classification problems. Neural networks have been used for a wide variety...
Neural networks tackle real-world problems. (Technology Update)(includes related article on how neural network technology works)
; Neural networks tackle real-world problems Neural networks mimic the human brain; they operate on experience...software and hardware products to implement artificial neural networks and solve real problems. In particular, neural networks...
Neural networks gaining foothold in business world Technology helps software think for itself
; Long an exotic field of computing, neural networks are beginning to show up in everyday...more for itself. In recent years, neural networks have moved out of academia and high...to generate a donation. In short, neural networks helped A.B. Data show that 5% of one...
Three-step method evaluates neural networks for your application. (includes related article on seven design steps for back-propagation neural networks) (Tutorial)
; ...network can do the thinking for you. Neural networks are the core of many well-known applications...methodology would explain why and when neural networks could be useful and would help you...evaluate three ways that you can use neural networks in an automated assembly and test...
AI-based neural networks.
; Al-Based Neural Networks The latest in information-processing...business computing marketplace, neural networks are now in the information technology...forecasts seem to indicate that neural networks will be a significant part of...
Applying neural networks to predicting battle outcomes
; ...accurate forecast from chaotic data. Neural networks were used for investigating time and...to analyze this type of data, such as neural networks. Kosko ( 1992) states, "Neural networks . . . unlike statistical estimators...
Laboratory support for the teaching of neural networks
; ...past six years in teaching a graduate neural networks subject are reported. Various neural...architecture5, parallel computing6 and indeed neural networks-9. Since our primary interest in computer...of the present paper. 2 ARTIFICIAL NEURAL NETWORKS The foundations of artificial ...
What neural networks really do. (includes related articles on history of neural networks, real-world products)
; What neural networks really do Computer-based neural networks aren't new, but they are finally becoming useful...to financial forecasting. There is one caveat: Neural networks aren't supplanting existing technologies but working...
Neural networks: Here, there, and everywhere--an examination of available intellectual property protection for neural networks in Europe and the United States
; 1. Introduction The development of neural networks, engineering constructs that simulate...the scope of its initial training.4 Neural networks differ from other forms of "artificial...analysis, and target recognition.7 As neural networks gain popularity and their use expands...