Neural networks for cost estimation: Simulations and pilot application

An Accuracy Investigation of Product Cost Estimation in Automotive Die Manufacturing

“…However, they were unable to confirm the accuracy of their method either, due to a too small data sample, or the method, or to the high error rate obtained. Furthermore, Bode mentions that they were unable to use real cost information to attempt to validate his developed approach (Bode, 2000). Nevertheless, in some cases, some authors made use of a simulation procedure, attempting to emulate the cost information from a production setting to enable them to test the accuracy of their method (Bode, 2000).…”

“…Furthermore, Bode mentions that they were unable to use real cost information to attempt to validate his developed approach (Bode, 2000). Nevertheless, in some cases, some authors made use of a simulation procedure, attempting to emulate the cost information from a production setting to enable them to test the accuracy of their method (Bode, 2000). The results of the literature review on accuracy testing in cost estimation have been summarized in table 2, showing which author has developed which type of cost estimation method and whether a validation was attempted or not.…”

Comparison of School Building Construction Costs Estimation Methods Using Regression Analysis, Neural Network, and Support Vector Machine

“…[6]. For example, the RA model [7][8][9], NN model [10][11][12][13], SVM Model [6,[14][15][16], and CBR model [1,17,18] have been developed for predicting or estimating construction costs. Approaches to cost estimation based on statistics and linear regression analysis have been developed since the 1970s [2].…”

“…Previous studies [2,12,[20][21][22] revealed that an NN model for cost estimating is superior to the RA model. Also, the accuracy of cost estimation based on the SVM technique is similar to that of cost estimation based on RA [23].…”

“…neural network and support vector machine) could be examined through regression analysis. using regression analysis have several disadvantages: 1) they have no specific, or clearly defined, approach that will help estimators choose the cost model that best fits the historical data to a given cost estimating application [12,20,24,25]; 2) a certain type of multiple equation and its data are assumed to be similar to be suitable for the regression equation [12,24,25]; 3) the variable influencing the estimation must be reviewed in advance, and it is also difficult to use a large number of input variables [24][25][26]. However, regression analysis, as it is usually called, is a very powerful statistical tool that can be used as both an analytical and predictive technique in examining the contribution of potential new items to the overall estimate reliability [27].…”