Cost estimation by artificial neural networks

Pao Yue-kong Library Electronic Theses Database

Cost estimation by artificial neural networks


Author: Chan, Fung-ming Ada
Title: Cost estimation by artificial neural networks
Degree: M.Sc.
Year: 1995
Subject: Building -- Estimates -- Data processing
Neural networks (Computer science)
Hong Kong Polytechnic University -- Dissertations
Department: Multi-disciplinary Studies
Pages: 90 p. : ill. ; 30 cm
Language: English
InnoPac Record:
Abstract: This report described what I have tried in the past year in the study of applying neural network in cost estimation in construction industry. Neural network is a new technology and has been developed for about 30 years. It has been successfully applied in many areas including cost estimation, financial control and complicated computation. The major selling point of neural network is its ability to learn and to solve any problem in the presence of 'noise'. The ability to learn is important to application in cost estimation and prediction because the factors affecting the cost will change from time to time. Any rule based system which can solve a problem at the present moment could not ensure that they can do it after ten years. Besides, learning help the system adjust their approach of prediction once the result goes wrong. 'Noise' has been an obstacle to the accuracy of estimation for a long time. With a sound technique to remove this, it is expected that the accuracy could be improved. These are the main reasons why I consider that neural network can be employed for cost estimation in construction industry. A system called "Super Estimator" has been designed for cost estimation in construction industry. It can estimate the cost of a particular works item based on some market conditions, which has to be inputed by the user. When the cost of all major works items have been worked out by the program, the total cost of a project will become available. The system is found user-friendly and its accuracy of estimation is satisfactory for tendering, planning and preliminary estimation. Its accuracies are 26%, 54% and 76% for tendering, planning and preliminary estimation purpose respectively. These are considered as a good estimation and adequate to achieve the objective of the research. I am delighted to see the accuracy of the system and so would like to recommend this program to practicing engineers, architects and project managers who can improve their cost estimation by the system.

Files in this item

Files Size Format
b12259743.pdf 3.391Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.


Quick Search


More Information