Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.17559/TV-20150116001543

Construction costs forecasting: comparison of the accuracy of linear regression and support vector machine models

Silvana Petruseva orcid id orcid.org/0000-0002-3752-513X ; Faculty of Civil Engineering, "Ss. Cyril and Methodius" University, Blv. Partizanski Odredi, 24, 1000 Skopje, Republic of Macedonia
Valentina Zileska-Pancovska orcid id orcid.org/0000-0001-7620-4040 ; Faculty of Civil Engineering, "Ss. Cyril and Methodius" University, Blv. Partizanski Odredi, 24, 1000 Skopje, Republic of Macedonia
Vahida Žujo orcid id orcid.org/0000-0003-3380-5828 ; Faculty of Civil Engineering, University Dzemal Bijedic, Univerzitetski Kampus, 88104 Mostar, Bosnia and Herzegovina
Aida Brkan-Vejzović ; Faculty of Civil Engineering, University Dzemal Bijedic, Univerzitetski Kampus, 88104 Mostar, Bosnia and Herzegovina


Puni tekst: hrvatski pdf 989 Kb

str. 1431-1438

preuzimanja: 542

citiraj

Puni tekst: engleski pdf 989 Kb

str. 1431-1438

preuzimanja: 1.987

citiraj


Sažetak

Each contract for a construction project has the costs as an essential element, so the accuracy of forecasting the construction costs can have an impact on the project realization, and also, on the project participants’ business. Data for structures (75) were used for modelling with two predictive models: linear regression model (LR) and support vector machine (SVM) model, using Bromilow’s model for cost and time relation and predictive modelling software DTREG. The mean absolute percentage error (MAPE) for the SVM model is 0.3% and for the linear regression model is 4.79%. Comparison of the models’ results pointed out that the forecasting with SVM was significantly more accurate.

Ključne riječi

construction costs; forecasting; linear regression; support vector machine

Hrčak ID:

188240

URI

https://hrcak.srce.hr/188240

Datum izdavanja:

25.10.2017.

Podaci na drugim jezicima: hrvatski

Posjeta: 3.618 *