Expert System Approach To Overcoming Excessive Cost On Building Sites
Project managers need accurate estimate of building projects to be able to choose appropriate alternatives for their constructions. Estimated costs of building projects, which hitherto have been based on regression models, are usually left with gaps for high margin of errors and as well, they lack the capacity to accommodate certain intervening variables as construction works progress. Data of past construction projects of the past 2 years were adjusted and used for the study. This model is developed and tested as a predictive cost model for building projects based on Multilayer Perceptron Artificial Neural Networks (ANNs) with Levenberg Marqua. This model is capable of helping professionals save time, make more realistic decisions, and help avoid underestimating and overestimating of project costs. The model is a step ahead of Regression models.
1.1 Background Of The Study
A number of uncompleted and abandoned projects are attributable to overall bad projects management of which poor forecasting approach is a factor. Poor cost forecasting approach will lead to underestimating or over estimating and consequently cost overrun. Project abandonment as a result of cost overrun arising from poor cost forecasting approach, is an interesting phenomenon locally as well as globally.
This phenomenon has led to various stakeholders in built environment to be aware of importance of accurate project cost right from conceptual stage of building project as well as throughout the life cycle of the project work. The awareness of working with accurate cost has thus created a trend among various clients including private, corporate, as well as public clients (government), that prudency in resources allocation is a great necessity for successful execution of project works. Thus in a bid to have an appreciation of what the project cost should be, clients resort to request for cost implications of various aspect of the project for purpose of planning, so also to have better appreciation of magnitude of project cost and environmental cost implication of the project as well as impact of the projects financial implication on client’s and other stakeholders decision. This development led to the advent of forecasting project cost so as to generate project cost information which reveals what the value of a project cost could be in future. However, in providing project cost information, cost estimator often resort to using traditional approach, recent developments on the other hand has proven the fact that traditional approach, which uses historical methods do not tend to capture the details of project works cost components, as well as intervening variables that impacts the cost magnitude. Without gainsaying once the process is faulty, the end result could not be anything less to an incomplete account of project’s cost and cost overrun.
The cube method was the first recorded forecasting method; this was invented about 200 years ago, floor area approach was developed around 1920 , some researchers later developed storey enclosure method on 1954, which provides better result over the previously developed cube and floor area, certain variables were identified and incorporated into the model other than those used in the past, like floor areas vertical positioning, storey heights, building shape and presence of basement.
However in the mid-1970s, researchers started deploying statistical techniques cost modeling, through these, conventional methods evolved, such as approximate quantities and optimization. Peculiar to the research work in this era is possibility of demonstrating the applicability of the developed models, as a result of seemingly non applicable nature of model generated.
1.2 Statement Of The Problem
Construction projects are very different from products manufactured in assembly lines: each building is unique, and this applies even for groups of buildings that look similar externally. Due to this fact, construction cost estimation must be performed individually for each project. This approach is very different from assembly line manufacturing, where all products are identical and have the same cost.
Inaccurate cost estimation is detrimental for construction projects. Both overestimation and underestimation have negative consequences: When costs are overestimated, the owner ends up paying more than necessary or may decide not to proceed with the project. Contractors can also face negative consequences if they overestimate project costs: they are likely to lose in competitive bidding or they may be regarded as scammers, hurting their reputation. When costs are underestimated, there are many unforeseen expenses during the construction phase. Based on how the contract is structured, these costs may affect the owner, the contractor, or both. There have been cases where developers or contractors end up bankrupt due to drastic underestimation in a large project.
1.3 Objective Of The Study
The objective of this study is to highlight an expert model for overcoming excessive cost on project sites. The Data of past construction projects of the past 2 years were adjusted and used for the study. This model is developed and tested as a predictive cost model for building projects based on Multilayer Perceptron Artificial Neural Networks (ANNs) with Levenberg Marqua. This model is capable of helping professionals save time, make more realistic decisions, and help avoid underestimating and overestimating of project costs. The model is a step ahead of Regression models.
1.4 Research Methodology
The method used in carrying out the work is in two stages; the design stage, modeling stage (training stage) and the testing (validation) stage
Summary And Conclusion
The analysis carried out in the study, presents preliminary validation of prospect of obtaining a model that will predict building construction cost with minimum error, this also demonstrates the applicability of Neural network in forecasting the cost of building work. The result of the analysis indicates high level of accuracy in the output obtained from the neural network model with maximum variation factor of 7.42 percent. The corruption escalator factor and inflation buffer factored into the Bill value accounts for this variation. This indicates that in predicting value for subsequent project cost, the percentage can be factored into such cost to arrive at the actual cost value for such project. It is believed that the model will be suitable for use at different stages of project work.
How To Get The Complete Material For Expert System Approach To Overcoming Excessive Cost On Building Sites
The complete material will be sent to your email address after payment
( Quick & Simple)
|FOR CLIENTS IN NIGERIA:|
|CLICK HERE to make purchase (₦3,000)|
|FOR CLIENTS OUTSIDE NIGERIA:|
|CLICK HERE to make purchase ($15)|
This research material “Expert System Approach To Overcoming Excessive Cost On Building Sites” is for research purposes and should be used as a guide in developing your research project / seminar work. For no reason should you copy word for word (verbatim) as samphina.com.ng will not be liable for any who copied the material.
The aim of providing this material is to reduce the stress of moving from one school library to another all in the name of searching for research materials. This service is legal because, all institutions permit their students to read previous projects, books, articles or papers while developing their own works. According to Austin Kleon “All creative work builds on what came before”.
samphina.com.ng is only providing this material “Expert System Approach To Overcoming Excessive Cost On Building Sites” as a reference for your research. The paper should be used as a guide or framework for your own paper. The contents of this paper should be able to help you in generating new ideas and thoughts for your own research. Use it as a guidance purpose only.