Predicting Future DoD Material Obsolescence Under Uncertainty: AI-enabled Identification and Modeling of Risk-based Factors Derived from U.S. Industry -specific Business Verticals

Predicting Future DoD Material Obsolescence Under Uncertainty: AI-enabled Identification and Modeling of Risk-based Factors Derived from U.S. Industry-specific Business Verticals is a research-based, analytically rigorous mix-methods approach centered on the creation, application, and execution of cloud-based Artificial Intelligence (AI) / Machine Learning (ML) advanced modeling and simulation, qualitative and quantitative AI / ML algorithm integration, and synthesized algorithm execution capabilities.  The structural design, development, demonstration, delivery, and deployment of these cloud-based AI / ML capabilities is informed through the exhaustive examination of risk-based factors derived from U.S. industry-specific verticals – Automotive, Banking, Healthcare, Insurance, Industrial Manufacturing, Insurance, and Oil & Gas – where the focal industry firm is financially motivated to aggressively apply AI / ML methods designed to significantly increase shareholder value or significantly decrease strategic risks.  These AI / ML methods are applied to specific perceived or actual risk conditions of uncertainty, including bi- or multi-directional decision trade space boundary considerations of Customer, Contract, Financing, Manufacturing Standards, Material, or Policy implications.  Other areas of risk qualification under uncertainty may include Economic Conditions, Government Regulation, and Human Resources.  The creation and application of AI / ML high speed algorithms deployed in response to the various risk conditions of uncertainty found within each industry-specific vertical provide a unique foundational framework for addressing the DoD’s uncertain future concerning material obsolescence, a phenomenon which is becoming the primary factor impacting material availability and, in-turn, weapon system availability across the MilSvs.  Material obsolescence is an evolutionary state condition.  In other words, the obsolescence of specific weapon system materials does not instantly appear, it is a state condition that evolves over some period of time until the final condition of obsolescence is observed.  As a state condition, material obsolescence can be objectively modeled through the theoretical lens of survival analysis as applied using effectivity modeling via game theory.  This research employs a mixed methods (qualitative and quantitative) AI / ML algorithmic modeling strategy to evaluate a portfolio of risk uncertainties that may be responsible for enabling the material obsolescence condition.  These insights then serve to inform development of the predictive AI / ML modeling parameters required to predict future DoD weapon system material obsolescence conditions.  The power of the predictive AI / ML modeling as applied to material obsolescence provides the DoD a portfolio of time-phased management strategies to effectively mitigate material obsolescence.