Naval Expeditionary Readiness Model

Loading...
Thumbnail Image
Authors
MacKinnon, Douglas J.
Davenport, Branden W.
Subjects
Naval Expeditionary Forces
Forecasting
Budget
Readiness
Advisors
Date of Issue
2024-01
Date
Publisher
Monterey, California. Naval Postgraduate School
Language
Abstract
Naval expeditionary forces lack the ability to adequately estimate the level of spending required to achieve a minimum level of readiness. Currently the Navy Expeditionary Combat Enterprise (NECE) Capability Costing Model (NCCM) forecasts requirements using Excel Solver and data from the Optimized Fleet Response Plan (OFRP) and Certified Obligation Reports. To explore methods of improving requirement forecasts, this research limits its focus to one program, Explosive Ordinance Disposal (EOD), one component, active duty, and one training and testing data split. It then attempts multiple forecasting methods over multiple levels of cost aggregation. These forecasting methods include Exponential Smoothing, Autoregressive Integrated Moving Averages (ARIMA), and dynamic regression models. The analysis then evaluates models made with those methods using the accuracy measures of absolute error (MAE), mean absolute percentage error (MAPE), and mean absolute scaled error (MASE). It also attempts hierarchical models to forecast costs and evaluates those models in the same way. Finally, it calculates forecasts for two years in the future and compares those forecasts to actual costs. This final calculation mimics the process required in the Program Objective Memorandum (POM) process. This technical report finds that the various models forecast at different levels of accuracy across different levels of cost aggregation. The most accurate model to forecast total EOD costs two years in the future is an ARIMA model. It possesses a 10 percent delta in its forecast. The best aggregated model is an exponential smoothing model for the Budget Submitting Office (BSO) 60 and the warfare pillars of personnel (P) and training (T). Its delta is three percent. However, some levels of aggregation are much worse, with the best model possessing a delta of 36 percent for BSO 70 for supply (S) and equipment (E) costs. This technical report ends with several recommendations for future research.
Type
Technical Report
Description
Organization
Identifiers
NPS Report Number
NPS-OR-23-013
Sponsors
Naval Research Program (NRP); Integration of Capabilities and Resources (N81); Service Integration and Policy, Washington, DC
Funder
This research is supported by funding from the Naval Postgraduate School, Naval Research Program (PE 0605853N/2098)
Format
55 p.
Citation
Distribution Statement
Approved for public release; distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
Collections