Application of Multiple Regression and Artificial Neural Networks as Tools for Estimating Duration and Life Cycle Cost of Projects

2022 ◽  
pp. 509-540
Author(s):  
Brian J. Galli
Keyword(s):  
Life Cycle ◽  
Multiple Regression ◽  
Life Cycle Cost ◽  
Network Models ◽  
Neural Network Models ◽  
Statistical Tools ◽  
Planning Project ◽  
Statistical Approaches ◽  
Artificial Neural ◽  
Face Complex

Project managers face complex challenges when planning project stages because contract durations and project costs are difficult to predict accurately. The purpose of this study is to investigate statistical tools and concepts that can be integrated in the second phase of the project life cycle: the planning stage. Furthermore, this study aims to compare the accuracy of multiple regression and artificial neural network models, as well as the application of simulation in construction models used in predicting project duration and cost. This paper will also discuss the industry's current estimation methods, the use of statistical approaches, simulation, and the relationship between the application statistical tools and project success. Thus, this review identifies the trending statistical tools used by scholars to develop regression and neural models to solve the complexity of cost and duration estimation. The findings indicate that although the industry needs more accurate predictions and estimating tools, and regardless of the investigations and advancements made with integrating statistical tools, implementing these statistical approaches is faced with barriers.

scholarly journals Application of Multiple Regression and Artificial Neural Networks as Tools for Estimating Duration and Life Cycle Cost of Projects

2020 ◽  
Vol 7 (1) ◽  
pp. 1-27
Author(s):  
Brian J. Galli
Keyword(s):  
Life Cycle ◽  
Multiple Regression ◽  
Life Cycle Cost ◽  
Estimation Methods ◽  
Second Phase ◽  
Neural Network Models ◽  
Statistical Tools ◽  
Planning Stage ◽  
Statistical Approaches ◽  
Artificial Neural

Project managers face complex challenges when planning project stages because contract durations and project costs are difficult to predict accurately. The purpose of this study is to investigate statistical tools and concepts that can be integrated in the second phase of the project life cycle: the planning stage. Furthermore, this study aims to compare the accuracy of multiple regression and artificial neural network models, as well as the application of simulation in construction models used in predicting project duration and cost. This paper will also discuss the industry's current estimation methods, the use of statistical approaches, simulation, and the relationship between the application statistical tools and project success. Thus, this review identifies the trending statistical tools used by scholars to develop regression and neural models to solve the complexity of cost and duration estimation. The findings indicate that although the industry needs more accurate predictions and estimating tools, and regardless of the investigations and advancements made with integrating statistical tools, implementing these statistical approaches is faced with barriers.

scholarly journals Artificial neural networks incorporating cost significant Items towards enhancing estimation for (life-cycle) costing of construction projects

2013 ◽  
Vol 13 (3) ◽  
pp. 51-64 ◽  
Author(s):  
Ayedh Alqahtani ◽  
Andrew Whyte
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Life Cycle ◽  
Life Cycle Cost ◽  
Construction Projects ◽  
Back Propagation ◽  
Neural Network Models ◽  
Artificial Neural ◽  
Excel Solver

Industrial application of life-cycle cost analysis (LCCA) is somewhat limited, with techniques deemed overly theoretical, resulting in a reluctance to realise (and pass onto the client) the advantages to be gained from objective (LCCA) comparison of (sub)component material specifications. To address the need for a user-friendly structured approach to facilitate complex processing, the work described here develops a new, accessible framework for LCCA of construction projects; it acknowledges Artificial Neural Networks (ANNs) to compute the whole-cost(s) of construction and uses the concept of cost significant items (CSI) to identify the main cost factors affecting the accuracy of estimation. ANNs is a powerful means to handle non-linear problems and subsequently map between complex input/output data, address uncertainties. A case study documenting 20 building projects was used to test the framework and estimate total running costs accurately. Two methods were used to develop a neural network model; firstly a back-propagation method was adopted (using MATLAB SOFTWARE); and secondly, spread-sheet optimisation was conducted (using Microsoft Excel Solver). The best network was established as consisting of 19 hidden nodes, with the tangent sigmoid used as a transfer function of NNs model for both methods. The results find that in both neural network models, the accuracy of the developed NNs model is 1% (via Excel-solver) and 2% (via back-propagation) respectively.

Sign in / Sign up

Export Citation Format

Share Document