MODEL FOR CONSTRUCTION BUDGET PERFORMANCE - NEURAL-NETWORK APPROACH

A neural network approach is used to identify the key management facto rs that affect budget performance in a project. Field data of project performance has been used to build the budget performance model. This approach allows the model to be built even if the functional interrela tionships between input factors and output performance cannot be clear ly defined. Altogether eight key determining factors were identified c overing areas related to the project manager, project team, and planni ng and control efforts, namely: number of organizational levels betwee n project manager and craftsmen, project manager experience on similar technical scope, detailed design complete at start of construction, c onstructability program, project team turnover rate, frequency of cont rol meetings during construction, frequency of budget updates, and con trol system budget. The model is able to give good predictions even wi th previously unseen data and incomplete information on the key factor s. The model can be used to evaluate various management strategies and thus resources can be effectively deployed to strengthen these aspect s of project management.