Forecasting Suitable Supplier for Construction Project Using Machine Learning Techniques

Abstract

The aim of the research is to forecast the suitable suppliers for construction project using machine learning techniques. Firstly the librarian studies were conducted and research gap is extracted. Then innovation was determined. Based on the innovation a model for suitable supplier forecasting for construction project using machine learning techniques were provided. The model includes 12 entry variables and 1 output variable that include supplier performance. The model using 2 algorithm of artificial neuron network and support vector machine were conducted and the most influencing factors were determined using decision tree algorithm. The general comparison between artificial neuron network and support vector machine indicate the better performance of artificial neuron network based on decision tree. Based on decision tree results we can say that the supplier company income is considered as most important variable. The order change cost variable play the separator role in lower level. The life variables of companied and guarantees after company income and change cost of order play the main role.