Neural networks for construction project success

Abstract Being able to identify key attributes for successful project performance is of paramount importance to project owners, contractors, and designers. Understanding these key factors can help in the efficient execution of a construction project. This paper identifies key project management attributes associated with achieving successful budget performance using a neural network approach. Neural network models were developed using field data comprising potential determinants of construction project success. Altogether eight key project management factors were identified: (1) number of organizational levels between the project manager and craft workers; (2) amount of detailed design completed at the start of construction; (3) number of control meetings during the construction phase; (4) number of budget updates; (5) implementation of a constructability program; (6) team turnover; (7) amount of money expended on controlling the project; (8) the project manager's technical experience. The final model, after sufficient training, can also be used as a predictive tool to forecast budget performance of a construction project. This approach allows the budget performance model to be built even though the functional interrelationships between inputs and output are not clearly defined. The model also performs reasonably well with incomplete information of the inputs.