Structured and Unstructured Data Sciences and Business Intelligence for Analyzing Requirements Post Mortem

Loading...
Thumbnail Image
Authors
Kendall, Walter Anthony
Zhao, Ying
Schwamm, Riqui
Subjects
Requirements
cost growth
Advisors
Date of Issue
2022
Date
2022
Publisher
Monterey, California: Naval Postgraduate School
Language
Abstract
The objective is to review requirements created within the DoD Requirements process and identify those that create excessive cost growth, and rank programs with significant cost growth. The research questions are: ' What are common elements of requirements that create excessive cost growth in Navy systems? ' Assuming the elements are identified, determine the risk (likelihood and magnitude) of cost growth from common elements for both procurement and sustainment costs. We propose structured and unstructured data sciences and business intelligence to address the research questions: ' Apply text analyses to the DoD programs requirements data from the operational requirements documents and previous processes. Locate the cost growth risks (likelihood and magnitude) in terms of characteristics including capability requirements (unstructured), key performance parameters (structured data), key systems attributes (structured data), keywords, themes, and entities. Tools include lexical link analysis, spaCy (https://spacy.io/), Orange, and https://prodi.gy/ (for classification). ' Apply Network/graph tools: visualize the risks and capabilities in terms of relations. Prioritize capability, program, system, or product using centrality analysis and correlate with the cost growth risk. ' Apply the integrated deep analytics of leveraging AI for learning, optimize, and wargame (LAILOW) framework, derived from the ONR funded projects. Patterns are learned from big data (if any) and used for the optimization of what if analysis. New operation and capability requirements anticipate uncertainty, unknowns, and unexpected situations when there is no or rare data. This motivates using wargame simulations to coevolve risks and capabilities using coevolutionary algorithms of selection, mutation, and crossover. The tasks include scoping the data and demonstrating the proposed methods. The deliverables include reports, a demonstration, and a paper approved by the sponsor.
Type
Poster
Description
NPS NRP Project Poster
Department
Information Sciences (IS)
Organization
Naval Research Program (NRP)
Identifiers
NPS Report Number
Sponsors
N8 - Integration of Capabilities & Resources
Funder
This research is supported by funding from the Naval Postgraduate School, Naval Research Program (PE 0605853N/2098). https://nps.edu/nrp
Chief of Naval Operations (CNO)
Format
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