Extreme Learning Machines (ELM) as Smart and Successful Tools in Prediction Cost and Delay in Construction Projects Management

The construction industry is subject to a high level of risks and uncertainties than any other industry. In reality, most participants experience cost and time overruns risks and often fail to meet quality standards and operational requirements. This paper aimed to investigate the accuracy of artificial intelligent models such as Extreme Learning Machines (ELM) to demonstrate the impact of risk factors on predicting the cost and delay of construction projects. Risk factors (RF) and delay factors (DF) were identified and analyzed using Probability and Impact analysis adopted as the model's inputs. At the same time, the outputs for the models were represented by the ratio of contractor's profit to project costs and the period of delay occurring in the construction projects. Root mean squared error (RMSE), correlation coefficient (R), and coefficient of determination (R2) were employed as performance indices of the models to evaluate the accuracy of the results. The study results showed that the ELM model has demonstrated acceptable performance in predicting the cost and delay, resulting in superior performance indices.