brianletort.ai

AI Transformation Library

See how AI changes the work.

102 real-world cases. What changed, what improved, and where people still decide.

CardsTable

6 cases

1–6

CaseAI valueOpen
An editorial scene for Netherlands Tax and Customs Administration / Benefits contrasts reviews applications and available records to select suspected fraud for investigation. with scores applications using dozens of indicators, including citizenship, and selects cases as suspicious. in the self-learning risk-classification model for benefit applications workflow.
Netherlands Tax and Customs Administration / Benefits		The Dutch Data Protection Authority found improper and discriminatory processing from at least March 2016 to October 2018 because nationality was used in the model.
An editorial scene for EY contrasts defines the risk population and selects transactions for testing under ey's sample-first baseline. with loads general-ledger and subledger data and runs full-population analyses across erp systems. in the ey helix full-population general-ledger analysis workflow.
EY		Approximately 480 billion general-ledger lines loaded into the US analyzer in FY2025
An editorial scene for HSBC contrasts screen transactions against predefined parameters and generate alerts. with score transactions and identify suspicious activity using an ai model trained on hsbc data. in the dynamic risk assessment transaction monitoring workflow.
HSBC		HSBC reported 60% fewer alerts while identifying two to four times as much suspicious activity.
An editorial scene for Mastercard contrasts scores transactions from account, merchant, device, and purchase features. with analyzes entity relationships across a much larger graph and improves the risk score in under 50 milliseconds. in the decision intelligence pro graph-based transaction risk scoring workflow.
Mastercard		Mastercard's initial modeling showed 20% average fraud-detection improvement.
An editorial scene for U.S. Department of the Treasury, Bureau of the Fiscal Service contrasts review payment and bank information through existing fraud processes. with scores and prioritizes potentially fraudulent treasury checks in near real time. in the near-real-time machine-learning prioritization of potentially fraudulent treasury checks workflow.
U.S. Department of the Treasury, Bureau of the Fiscal Service		$1 billion recovered in FY2024; Treasury separately reported $375 million recovered in FY2023
An editorial scene for Danske Bank contrasts apply human-authored fraud rules to transactions. with score millions of transactions in real time using learned patterns and latent features. in the machine-learning and deep-learning transaction fraud scoring workflow.
Danske Bank		Vendor case study reports 60% fewer false positives and 50% more true positives
Curated collections →Evidence methodologyPublication history
AI Transformation Library | Brian Letort