Application Of Data Mining Techniques For Conceptual Cost Estimation Of Selected Building Projects In Addis Ababa

Construction Technology And Management Project Topics

Get the Complete Project Materials Now! »

For project managers and decision makers, developing an accurate cost estimate in thernconceptual stage of a project is a crucial but challenging task. Different techniques and methodsrnhave been devised and researched to accurately estimate the cost of building projects at thernpreliminary stages. These methods can broadly be divided into two based on the approach theyrnfollow. The cost –based or parametric cost modeling approach uses historical cost data andrndifferent Data Mining techniques to develop a cost prediction model. The second method usesrna bottom-up or quantity strategy, in which data on the quantity of works is utilized to constructrnquantity prediction models for each work item. These predicted quantities can then bernmultiplied by their current unit rates to determine the respective costs. In this study a parametricrncost model is first developed to assess its accuracy in predicting the final cost of buildingrnprojects based on historical data collected from selected building projects in Addis Ababa. Thisrnwas then followed by doing a comparison between the cost based and quantity basedrnapproaches by developing models for structural cost prediction as well as quantity models forrnthe different work items that make up the structural work (concrete, reinforcement, andrnformwork). Concurrently, the study explored the effectiveness of four data mining techniques,rnnamely Linear Regression (LR), Decision Trees (DT), Neural Networks (ANN), and GradientrnBoosted Trees (GBT) in estimating the final and structural cost of building projects. With arnrelative error of 37.05%, the ANN model was the most accurate in forecasting the final cost ofrna construction project, while the GBT model performed better in predicting structural costsrnwith a relative error of 22.67%. For quantity estimation models, the NN model showed superiorrnperformance for concrete and reinforcement quantity estimation with a relative errors ofrn16.44% and 19.32% respectively. The GBT model on the other hand performed better in rnformwork quantity estimation with a relative error of 19.58%. Accordingly, the total slab arearnwas identified to be the most important variable for all prediction. The study indicated thernquantity based approach provides more accurate cost prediction as opposed to the cost basedrnapproach for the case of structural cost estimation.

Get Full Work

Report copyright infringement or plagiarism

Be the First to Share On Social



1GB data
1GB data

RELATED TOPICS

1GB data
1GB data
Application Of Data Mining Techniques For Conceptual Cost Estimation Of Selected Building Projects In Addis Ababa

181