Presentation Information

[MS06-01]Clustering Philippine Jobs by Infectious Disease Spread Risk: A Machine Learning Approach

*Norvin Patadon Bansilan1, Jomar Fajardo Rabajante1 (1. University of the Philippines Los Baños (Philippines))

Keywords:

Machine Learning,Philippine Jobs,Clustering,Infectious Disease

Understanding the risk of infectious disease transmission across various occupations and industries is essential for improving workplace safety and public health strategies. Outbreaks such as tuberculosis or COVID-19 have shown that jobs involving frequent close contact such as healthcare, retail, or transportation, carry varying levels of exposure risk. This study applies machine learning clustering techniques to group Philippine jobs based on their susceptibility to infectious disease spread. Data on job characteristics such as number of encounters per hour, work shift duration, and crowd density were used to cluster occupations into distinct risk categories. The findings provide valuable insights into the varying levels of exposure inherent in different roles, offering a framework for designing targeted interventions, risk mitigation strategies, and evidence-based policies. This research highlights the potential of data-driven approaches in addressing occupational health risks in the Philippine context.