A Productivity Decision Support System for Construction Projects Through Machine Learning (ML)

Abstract

Productivity rate estimating is usually based on experience. It entails taking into account different factors, some of which are project specific while others are activity related. Conventional methods integrate the experience with stored data from previous projects. Such a process is often labor intensive and inaccurate. Consequently, accurate estimation of productivity rates through lessons learned is essential for efficient planning of projects. This paper proposes an automated decision support tool for productivity rate estimating through Machine Learning (ML). The adopted methodology (1) utilizes data from a set of completed projects; (2) defines a list of factors -that affect productivity estimates- based on comprehensive literature review and previous experiences; and (3) develops and compares the outcomes of automated Support Vector Machines (SVM) and Naive Bayes (NB) models for the assessment of productivity rates. The research methodology focuses on steel structures related activities including fabrication, delivery, and assembly. The models retrieve the closest case to a newly encountered one, including project description, project’s attributes, and activity’s attributes, and reports its estimated productivity and duration. This paper defines a pilot study aiming at developing a comprehensive automated estimator for the construction industry. The outcomes of the current research illustrate the potential of ML modeling to be adopted for assigning productivity rates, making it a powerful tool for decision making.