ACIS 2024 Proceedings

Abstract

Mental health and addiction service utilisation in New Zealand faces complex challenges marked by demographic disparities. This research conducts a comprehensive data mining project to address gaps in the literature, exploring demographic disparities in service utilisation and clustering clients by team types. Advanced analytical models optimise resource allocation and service delivery. The study design includes setting objectives based on literature gaps, collecting diverse data, cleaning, pre-processing, data reduction, and applying machine learning techniques. Random Forest Classifier and K-means clustering are used. Results involve visualisations and in-depth analyses, revealing demographic disparities with ethnicity, gender, and age influencing patterns. Clustering highlights distinct service demands within demographic groups, underscoring tailored interventions. Proposed actions include targeted programs, monitoring trends, collaboration, and public awareness. The findings emphasise the dynamic nature of mental health demographics and propose strategic actions to address disparities and enhance service delivery, aiming for a more responsive and equitable system.

Download

Share

COinS