A novel optimized neural network model for cost estimation using genetic algorithm

This study compared the performance, stability and ease of cost estimation modeling between conventional Artificial Neural Networks (ANN) and optimized ANN using Genetic Algorithm (GA) to develop cost estimating relationships. In this study, GA is employed not only to improve the learning algorithm, but also to reduce the complexity in parameter space. The GA optimizes simultaneously the connection weights between layers and the thresholds. In addition, GA reduces the dimension of the feature space and eliminates irrelevant factors. Results showed that optimized model has advantages in compare with conventional ANN in terms of accuracy, variability, model creation and model examination. Both simulated and actual data sets are used for comparison. © 2010 Asian Network for Scientific Information.