Using Machine Learning to Develop Occupational Interest Profiles and High-Point Codes for the O*NET System

Published:

November 2023

Tags:
Interests — Career Tools and Data
Authors:

Dan J. Putka, Jeffrey A. Dahlke, Maura I. Burke HumRRO

James Rounds University of Illinois

Phil Lewis National Center for O*NET Development

Summary:

This paper describes the successful effort to leverage advances in supervised machine learning to populate RIASEC Occupational Interest Profiles (OIPs) and high-point codes for 923 data-level O*NET-SOC occupations. Models developed use readily available information published within the O*NET database as input for generating OIPs and high-point codes for current and new occupations. As the world of work changes, these models can be applied to future versions of the O*NET database to generate and maintain high quality vocational interest information for the O*NET System.

The paper details each major phase of the project work. It concludes with finalized OIPs and high-point codes, along with guidance related to their future updates.

Download: