| Title |
A Study on Constructing a Computerized Algorithm of Forecasting Method for Monthly Expenditures by Historical Data Analysis |
| Keywords |
Expenditure Forecasting ; CBR(Case-based reasoning) ; Apartment Housing ; WBS ; Historical Cost Data |
| Abstract |
Dynamic and fragmented characteristics are two of the most significant factors that distinguish the construction business from other industries. The objective of this research is to explore a more precise forecasting method by applying Case-based Reasoning (CBR) to overcome these obstacles. The CAMP(CAse Matching Prediction), newly developed forecasting model in this study, enables project managers to forecast monthly expenditures with less time and effort by retrieving and referring only projects of a similar nature, while filtering out irrelevant cases included in database. For the purpose of accurate forecasting, 1) the choice of the numbers of referring projects and 2) the better selection among three levels ? which include a 20-work package level, a 7-major work package level, and a total sum level analysis, were investigated in detail. It is concluded that selecting similar projects at 12~19 % out of the whole database will produce a more precise forecasting.
The new forecasting model, which suggest the predicted values based on previous projects, is more than just a forecasting methodology; it provides a bridge that enables current data collection techniques to be used within the context of the accumulated information. This will eventually help all the participants in the construction industry to build up the knowledge derived from invaluable experience. |