Achieving Resilience Through Proactive Supply Chain Risk Management

Abstract

Utilizing robust training sets and historical data, the proposed DRME will employ a Bayesian model approach with proprietary feature extraction using deep learning to analyze as many as twenty-five different variables to predict and expose potential supply chain risks. Continuous real vs. hypothetical inputs will capture actions taken by supply chain managers and sourcing teams to proactively designate the best path forward and elevate supply chain management decision-making. The DRME will equip Rolls Royce with a deeper risk mitigation framework to identify risks and take action to resolve potential issues before they occur. Enhanced visibility through the ML-enabled DRME will equip Rolls-Royce and their sub tiers with the intelligence to monitor and verify ongoing supply network activities, track compliance, and ultimately gain extended visibility and control over sub-tier sourcing decisions to improve agility, impact to cost and overall operations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 11, 2023
Accession Number
AD1206202

Entities

People

  • Kami Bachman

Tags

Communities of Interest

  • Autonomy
  • Cyber
  • Engineered Resilient Systems
  • Space

DTIC Thesaurus Topics

  • Acquisition
  • Bayesian Networks
  • Business Administration
  • Commerce
  • Computer Programs
  • Dashboards
  • Data Sets
  • Environment
  • Lead Time
  • Machine Learning
  • Manufacturing
  • Materials
  • Risk Factors
  • Risk Management
  • Supply Chain
  • Training
  • User Interface

Readers

  • Defense Acquisition Program Management
  • Economics
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - DoD AI Strategy