Project success prediction using an evolutionary support vector machine inference model

Abstract

Accomplishing construction projects successfully requires continuous monitoring and control by construction managers of factors critical to project success. This research proposed using an Evolutionary Support Vector Machine Inference Model (ESIM) to predict project success dynamically. ESIM is a hybrid that integrates a support vector machine (SVM) with a fast messy genetic algorithm (fmGA). SVM is concerned primarily with learning and curve fitting, while fmGA deals primarily with optimization. Furthermore, the model integrates the process of Continuous Assessment of Project Performance (CAPP) to select factors that influence project success. Training and test patterns were collected from a CAPP database of 46 construction projects. These projects represent real data collected by Russell from 16 company members of the Construction Industry Institute (CII). Results show that ESIM is able to predict project success at a significant level of accuracy.