Application of 3-layer perceptrons to cost estimation

Abstract

During planning and design of new products design managers are interested in estimating cost as early as possible. Unfortunately, in an early design phase only a few attributes of the future product are known, and their impact on cost is not clear to the cost estimation expert. Neural networks might be able to detect hidden relationships between cost drivers and cost of a new product, and estimate cost afer being presented a small set of conceptual attributes describing the product. Based on a laboratory benchmark example with artijcial data we report about our experiments with classlJication perceptrons with one hidden layer. The attention is focused on the problem of small number of training samples available in the domain. The results of three possible remedies are presented, namely prewiring background knowledge, preprocessing input data, and transforming input data.

Neural networks for cost estimation: Simulations and pilot application

“…To date, only a few attempts to tackle cost estimation with neural networks are known (Ehrlenspiel and Schaal 1992, Becker and Prischmann 1993, Ko È nig 1995, Bode et al 1995b, 1995c, Bode and Ren 1996, Bode 1998. Becker and Prischmann (1993), and Ehrlenspiel and Schaal (1992) use curve-® tting multilayer perceptrons.…”

“…the number of past cases used for training, is small compared to common neural network applications and ranges from 10 to 200 (for results with other training set sizes see Bode et al 1995b). The reason is that in the domain of product development there are usually not many known past cases.…”

An empirical investigation into intelligent cost analysis in purchasing

“…In doing so, an ANN is trained with notionally generated data and a moderate accuracy of 40%-80% is achieved. They also point out some prerequisites that must be fulfilled for the use of ANN in cost analysis Bode et al (1995), Bode (2000) The backpropagation neural network was used in this study to construct an estimating model for the cost of plastic injection molding parts to reduce the complexity in traditional cost estimating procedures…”

Review of Cost Estimation Techniques and Their Strategic Importance in the New Product Development Process of Textile Products

“…The information is then processed by the hidden layers in order to be converted into the required output. And, finally, the output layer gives user output value that is a product cost (Bode, Ren & Shi, 1995;Stockton & Wang, 2004). Gurney, 1997) A schematic representation of the general cost estimation process by using neural networks is depicted in Figure 9.…”

“…The information is then processed by the hidden layers in order to be converted into the required output. And, finally, the output layer gives user output value that is a product cost (Bode, Ren & Shi, 1995;Stockton & Wang, 2004). Fig.…”