A Predictive Modeling Approach to Real-Time Resource Allocation in State-Funded Medicaid Programs
- Authors
-
-
Liton Das, Aksay damesh
Author
-
- Keywords:
- Sustainable Project Management (SPM), ESG Goals, Artificial Intelligence (AI), Project Lifecycle, Environmental Responsibility.
- Abstract
- Rising healthcare expenditures and uneven service delivery persist as chronic challenges within state-funded Medicaid programs, which serve millions of low-income and disabled Americans. Traditional retrospective budgeting methods fail to accommodate dynamic patient demand, leading to underfunded clinics, delayed treatments, and avoidable emergency department admissions. This study addresses the gap between static allocation models and real-time operational needs by proposing a predictive analytics framework that integrates machine learning classifiers with streaming claims data. The purpose is to design and evaluate a real-time resource allocation system that forecasts high-cost patient episodes and redistributes clinical resources accordingly. Using a quantitative, simulation-based methodology, the research analyzes synthetic Medicaid claims data modeled after three state programs (California, Texas, and New York) for 2023–2024. Key findings indicate that a gradient-boosting model (XGBoost) achieves 89.2% accuracy in predicting 72-hour high-risk events, enabling a 23.4% reduction in simulated wait times and a 15.7% decrease in avoidable hospital transfers compared to baseline retrospective allocation.
- Cover Image
-
- Downloads
- Published
- 05/12/2026
- Section
- Articles
- License
-
Copyright (c) 2026 Liton Das, Aksay damesh (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
A Predictive Modeling Approach to Real-Time Resource Allocation in State-Funded Medicaid Programs. (2026). The Science Post, 2(2). https://www.thesciencepostjournal.com/index.php/tsp/article/view/100