Construction project risk evaluation based on Rough Sets and Artificial Neural Networks

The construction industry is plagued by risk and often suffers poor performance as a result. Therefore, risk management is very important for construction project to achieve its goal. The risk evaluation is the basic work of risk management. There are a number of risk evaluation techniques, but each has its own faults. In this paper, a new model, which integrates Artificial Neural Networks and Rough Sets theory, was proposed to solve the construction project risk evaluation problem. Firstly, select index system for the risk evaluation of the construction projects and collect the data of projects as samples according to the index system. The decision table was formed accordingly. Experts discrete method is used to discrete the values of the attributes. Secondly, Genetic Algorithm was used to reduce the attributes in the decision table. Finally, Artificial Neural Networks model was built according to the index in the reduced attribute set. The testing result of the example indicates that the proposed model is satisfied in risk evaluation reliability, and the studying efficiency has improved compared with the simple Artificial Neural Networks method.