Optimizing Product Provenance Verification using Data Valuation Methods

arXiv — cs.LGFriday, December 5, 2025 at 5:00:00 AM
  • A novel data valuation framework has been introduced to enhance the selection and utilization of training data for machine learning models in Stable Isotope Ratio Analysis (SIRA), addressing challenges in verifying product provenance in global supply chains. This framework quantifies the marginal utility of samples using Shapley values, aiming to improve the accuracy of geographic origin verification amidst increasing geopolitical conflicts.
  • The development of this framework is significant for enforcement agencies, certification bodies, and companies involved in supply chain management, as it provides a more robust method for ensuring the authenticity of products. By optimizing data selection, it can lead to more effective regulatory compliance and consumer trust.
  • This advancement reflects a broader trend in artificial intelligence where explainability and data optimization are becoming crucial. The introduction of Sparse Isotonic Shapley Regression (SISR) highlights ongoing efforts to refine data valuation methods, addressing limitations in traditional approaches and emphasizing the importance of nonlinear explainability in AI applications.
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps
Continue Readings
ROSS: RObust decentralized Stochastic learning based on Shapley values
PositiveArtificial Intelligence
A new decentralized learning algorithm named ROSS has been proposed, which utilizes Shapley values to enhance the robustness of stochastic learning among agents. This approach addresses challenges posed by heterogeneous data distributions, allowing agents to collaboratively learn a global model without a central server. Each agent updates its model by aggregating cross-gradient information from neighboring agents, weighted by their contributions.
Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
PositiveArtificial Intelligence
A new study introduces regression-adjusted Monte Carlo estimators for calculating Shapley values and probabilistic values, enhancing the efficiency of these computations in explainable AI. This method integrates Monte Carlo sampling with linear regression, allowing for the use of various function families, including tree-based models like XGBoost, to produce unbiased estimates.

Ready to build your own newsroom?

Subscribe to unlock a personalised feed, podcasts, newsletters, and notifications tailored to the topics you actually care about