Using Workers Compatibility to Predict Labor Productivity through Cluster Analysis

Laura Florez*, Jean C. Cortissoz

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

8 Citations (Scopus)
25 Downloads (Pure)

Abstract

Masonry contractors seek to increase labor productivity by collecting detailed information on the workers productivity and the factors that influence productivity. Quantitative factors such as hours, activities, and tasks are often measured on site and are used to estimate productivity and determine times of construction. However, there may be qualitative factors such as personality that may also need to be measured on site because it can have a profound impact on the productivity of a crew. This paper proposes a mathematical framework that uses the personal compatibility between the workers in a crew to better estimate productivity. An instrument to measure and quantify personality is proposed to determine the compatibility of the workers in a crew. Cluster analysis principles are applied to group crews that share similar compatibility and productivity scores and use this information to empirically define a probability density function that will determine, for a given cluster, its average productivity. To illustrate how the function is used to predict the productivity of a crew, this paper presents an example applied in masonry construction in which times of construction and productivity are determined using the personal compatibility between the workers in the crew.

Original languageEnglish
Pages (from-to)359-365
Number of pages7
JournalProcedia Engineering
Volume196
DOIs
Publication statusE-pub ahead of print - 24 Aug 2017
EventCreative Construction Conference, CCC 2017 - Primosten, Croatia
Duration: 19 Jun 201722 Jun 2017

Keywords

  • cluster analysis
  • Masonry construction
  • probability density
  • productivity

Fingerprint

Dive into the research topics of 'Using Workers Compatibility to Predict Labor Productivity through Cluster Analysis'. Together they form a unique fingerprint.

Cite this