Improving the Personnel Records Scoring System for Air Force Active-Duty Officers and Enlisted Personnel

Kelly Hyde, Nelson Lim, Sarah Nicole Kosic, Anthony Lawrence, Alice Nguyen, Stephanie Williamson, Paul Emslie

ResearchPublished Oct 14, 2025

Cover: Improving the Personnel Records Scoring System for Air Force Active-Duty Officers and Enlisted Personnel

The authors expanded the Personnel Records Scoring System (PReSS) prototype, developed by RAND, to build a suite of tools to help U.S. Air Force (USAF) talent management stakeholders analyze the career development trajectories of both officer and enlisted personnel. 

PReSS is designed to improve the efficiency and objectivity of assessing whether personnel have fulfilled expectations for career progression by identifying promising candidates and providing an objective benchmark for comparing the actual decisions of raters and developmental team members. The system is a decision support tool that helps human resource personnel extract meaningful insights from unstructured text in officer and enlisted performance reports and structured administrative recordkeeping data.

The updated PReSS tool achieves higher accuracy based on more-stringent metrics, adapts more readily to potential changes in data over time, and provides deeper insights into the reasons behind the model’s predictions. 

Key Findings

  • Given enough information, an effective method, and sufficient computing resources, it is possible to quantify whether senior enlisted airmen and field grade officers have fulfilled the expectations for career development milestones, such as promotion, with high accuracy.
  • The features that correlate with promotion over the course of an airman’s career include some that are always relevant and others that become more or less relevant with increased seniority.
  • Although it is possible to predict career outcomes from just MilPDS quantitative features or just performance report qualitative features, the most-performant models use a combination of both.
  • The USAF already has the key information required for such a capability as PReSS to be operationalized on Envision, but some additional data that could further improve the models or expand PReSS’s use cases are not yet usable.

Recommendations

  • Operationalize PReSS for field grade officers and senior enlisted personnel and explore possible extensions of the tool using its outputs as a foundation for related capabilities, such as providing automated feedback to personnel.
  • Explore ways to analyze and use PReSS outputs to improve understanding and transparency of the key contributors to career outcomes throughout the course of an airman’s career, for both talent management stakeholders and personnel.
  • When operationalizing PReSS, emphasize the use and maintenance of the combined qualitative and quantitative Model 3, and ensure that both types of data remain up to date through robust and regular extraction pipelines.
  • Pursue opportunities to expand the scope of data available to PReSS, such as leveraging existing data connections that have not yet been used (e.g., MyVector) and collaborating with other USAF functions to establish new data connections where possible and relevant.

Topics

Document Details

Citation

Chicago Manual of Style

Hyde, Kelly, Nelson Lim, Sarah Nicole Kosic, Anthony Lawrence, Alice Nguyen, Stephanie Williamson, and Paul Emslie, Improving the Personnel Records Scoring System for Air Force Active-Duty Officers and Enlisted Personnel. Santa Monica, CA: RAND Corporation, 2025. https://www.rand.org/pubs/research_reports/RRA2996-1.html.
BibTeX RIS

Research conducted by

This publication is part of the RAND research report series. Research reports present research findings and objective analysis that address the challenges facing the public and private sectors. All RAND research reports undergo rigorous peer review to ensure high standards for research quality and objectivity.

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit www.rand.org/pubs/permissions.

RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.