Becoming Leaders in the Australian Construction Industry: A Machine Learning Analysis of LinkedIn Profiles
Diya Yan*, Yi Ding, Riza Yosia Sunindijo, Cynthia Changxin Wang, Zhengyi Yang
Australasian Universities Building Education Association Conference (AUBEA)
RAIDS Lab Authors
Details
Research Area
Tags
Resources
Abstract
As one of the most male-dominated industries in Australia, the construction industry should strive for a more inclusive and socially sustainable future, where leadership opportunities are accessible to diverse talent. While existing research has identified some barriers to career progression in construction through traditional survey and interview methods, this study aims to apply machine learning algorithms to investigate the role of gender in attaining managerial positions based on 3190 LinkedIn profiles. The classification algorithms, including Decision Trees, Ensemble Trees, and Neural Networks, were compared to determine the best-performing model. Then, the six adopted features, which relate to gender, work experience, educational background, and professional visibility, were ranked based on their contribution to the model's accuracy. Surprisingly, the results revealed that gender, often assumed to play a key role in career progression, was a non-contributing feature in the model. In contrast, the current company size, number of followers, and total duration of work experience emerged as significant predictors of higher managerial levels. These findings challenge gender assumptions and underscore the need for targeted strategies to enhance networking and visibility for supporting career advancement in the construction industry. This study contributes to the theoretical understanding of career progression by using a large-scale, data-driven machine learning approach. The results call for future studies to investigate predictors specific to career progressions and offer practical implications for fostering equitable and inclusive career pathways in the industry.