This paper introduces an AI-based model for solving the percent markup estimation problem. The model utilizes Neural Networks (NN), systems able to generalize solutions by learning from a set of examples representing different problem scenarios and their corresponding solutions or decisions. NNs simulate the decision Makers' process of acquiring experience and ability of producing reliable decisions to new situations, even if incomplete or noisy information is only available. In this paper, existing markup estimation models are reviewed and their limitations identified. The characteristics that render the problem more suitable for NN modelling are outlined The markup estimation process is analyzed and the decision-governing attributes identified. A hierarchical structure for the NN model is proposed. The model consists of four sub-networks, pertaining to the assessment of job uncertainty, job complexity, market conditions, and company capabilities. The results of the four networks form the input to a macro-level neural network designed to estimate the optimum markup and predict the expected profit, for a given project environment. A questionnaire survey is developed to elicit knowledge pertaining to current bid preparation practices of general contractors in the U.S.A. and Canada. Partial analysis of early received responses are utilized to structure, design, implement, train, and test the model's sub-network pertaining to the assessment of job uncertainty level. Issues regarding the implementation of the complete NN model, model validation, and integration with other decision analysis tools are also addressed.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £60 +P&P)