BUILDING A MODEL FOR PREDICTING PRODUCTIVITY AND EVALUATING FACTORS AFFECTING PRODUCTIVITY BY USING ARTIFICIAL NEURAL NETWORKS

Construction productivity is the main indicator of the performance of construction projects for any country. The productivity of construction projects is defined as the output of the system for each unit of input. The main objective of this paper is to identify and analyze factors affecting labor productivity in construction projects in Iraq through a closed questionnaire. While the second objective of this study is to construct a mathematical model for predicting the construction productivity for Formwork columns works. As well as, the assessment of factors affecting productivity using sensitivity analysis (Garson algorithm). After distributing, gathering and analysis the questionnaire and finding the relatve importance index (RII%) using the Likert scale for each influencing factor, the top ten factors were determined that effect on the productivity rate. As these factors are independent inputs of the model and affect the one output "dependent" is productivity rate. These factors are classified on the basis of the values of the relative importance index (RII%) calculated for each factor. Finally, the data were used in artificial neural networks (ANN) development of the prediction model. It was found that (ANN) have the ability to predict the Total productivity rate for formwork columns works for building project with a good degree of accuracy of the coefficient of correlation (R) was (94.39%) and average accuracy percentage of (AA%) was (85.45%). While, The sensitivity analysis indicated the following, The (V6) (Lack of labor surveillance) is ranked first with a relative importance of (27.61%). Contrast, The (V5) (The Ganger experience) has a low importance in the model with a relative importance around (0.35%) and it is ranked eleven