Date of Award

3-23-2017

Document Type

Thesis

Degree Name

Master of Science in Cost Analysis

Department

Department of Systems Engineering and Management

First Advisor

R. David Fass, PhD.

Abstract

Starting January 1, 2018, the Department of Defense new Blended Retirement System (BRS) will go into effect. Military members with less than twelve years of service will have the option to either remain in the current High 3 Retirement System or opt into the BRS. This decision will have a lasting impact on their lives well beyond their military careers. With this in mind, we have developed a Decision Support System that will enable service members to compare the two retirement choices in terms of annual and total lifetime expected value. There were three phases to the development of the decision support tool. First, we identified Simple Exponential Smoothing Method and Artificial Neural Networks as the most accurate forecasting techniques to predict the Thrift Savings Plan Funds’ rate of return. Next, we identified surrogate TSP portfolios based on minimizing downside risk. In the third phase, we identified risk tolerance and the continuation pay multiplier as the key drivers for differentiating between the two systems. Finally, the resulting Decision Support System leverages current time series forecasting techniques, behavioral economic theory, and Bayesian statistics to capture the complexity of this important decision while delivering relevant information to service members in a straightforward manner using an R Studio Shiny Application.

AFIT Designator

AFIT-ENV-MS-17-M-185

DTIC Accession Number

AD1051591

Download

Share

COinS