Year: 2026
Type: article
Abstract: Purpose This study aims to investigate the organisational factors that contribute to Australia’s persistent gender pay gap (GPG), which remains a challenge despite existing legislation. By analysing structural workplace factors like industry division and employer size, the authors use machine learning to build predictive models, moving beyond simply describing the problem to proactively identifying and addressing the specific drivers of pay disparity. Design/methodology/approach Using 2022–2023 data from the Workplace Gender Equality Agency (WGEA), the study analysed 7,800 Australian organisations. It used multiple machine learning models – including linear regression, random forest and neural networks – to predict the GPG based on employer and industry characteristics. Model performance was compared using R² and classification accuracy metrics. Findings Neural networks achieved the highest accuracy (91.9%), showing that employer size, sector and leadership composition are key predictors of the GPG. Sectors such as financial services, construction and mining exhibited the largest pay disparities. Surprisingly, the presence of flexible work policies correlated with higher GPGs, suggesting these policies may be reactive measures rather than indicators of equitable workplace culture. Originality/value This research is among the first to apply AI-driven algorithmic modelling techniques to the WGEA data set for GPG prediction. The paper offers a twofold contribution by providing novel insights into how specific organisational attributes influence pay equity: academically, it advances methodological lens within gender studies by applying machine learning to a field traditionally dominated by econometric or qualitative methods. Practically, it provides a powerful new tool for regulators and organisations to identify the specific drivers of the GPG, allowing them to target interventions precisely where they are most needed.
Institutions: Adelaide University, The University of Adelaide
Language: English
Topic: Labour Market and Migration
Subfield: Gender Studies
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7155191641