The Personnel Records Scoring System: Volume 3, A Methodology for Designing Tools to Support Air Force Human Resources Decisionmaking
Abstract
The Department of the Air Force (DAF) has begun to develop and field artificial intelligence and machine learning (ML) systems for myriad mission areas and support functions, including human resource management (HRM). ML systems could accelerate existing decision processes and enhance decision quality by leveraging data. Further, by allowing the DAF to make decisions at greater speed and scale, ML systems have the potential to enable entirely new decision processes. One of the richest sources of personnel data available to the DAF is performance reports. Information about service members knowledge, skills, abilities, and other attributes is contained in these reports, along with supervisor assessments of their performance and leadership potential. This information could be used to directly inform selection boards and to indirectly inform a range of other HRM processes that consider service member experiences and performance. However, it is difficult to access and use this information because it is embedded in unstructured, narrative text. We propose a system that uses natural language processing to extract meaning from narrative text and make it available as inputs to a range of HRM processes. This report describes the methodology behind the system, known as the Personnel Records Scoring System (PReSS), and illustrates the primary output of the initial release of the systema general summary of performance information contained in an officers record.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 2024
- Accession Number
- AD1222474
Entities
People
- Cheryl K. Montemayor
- David Schulker
- Joshua Williams
- Li A. Zhang
- Matthew E. Walsh
Organizations
- RAND Corporation