Use case type

Fraud detection

Spots fraudulent transactions and behavior in real time by learning normal patterns and flagging anomalies.

Use cases

74

Examples

60

Industries

7

Timeline

20 mo

Data updated 1 day ago

Adoption over time

Documented cases per month

By case publish month · completed months only

60 cases documented across 37 months (Jul 23 – Jul 26), peaking at 8 in April 2026.

9 earlier cases before Jul 23 not shown

Each column counts every documented case of this type by its publish month, across the full corpus. The in-progress current month is excluded from columns and surfaced separately, and cases published before the charted window are summarized as earlier cases instead of plotted.

Company examples

Use cases of this type

10 shown from 74 use cases

Trustly is a global payment processing company that manages transactions between more than 110 million customers and merchants across more than 30 countries.The company migrated from private data centers and outsourced tools to AWS to improve fraud detection, transaction approval speed, visibility, and scalability.

TrustlyFinance

Inscribe built an agentic AI system for financial document fraud detection that reasons across documents, runs parallel forensic checks, searches the web for verification, and produces audit-ready fraud reports.The solution uses Amazon Bedrock for model selection and orchestration and Amazon SageMaker AI for proprietary fraud models, alongside AWS infrastructure services for ingestion, scaling, storage, and observability.

InscribeFinance

Deloitte Consulting LLP’s Bank Reconciliation Agent is an AI-powered solution that automates and enhances the end-to-end bank reconciliation process.The agent streamlines bank statement imports, GL transaction extraction, automated matching, and exception handling, while providing real-time fraud detection, FX adjustments, and continuous balance monitoring.

Deloitte Consulting LLPProfessional Services

Cockroach Labs describes a real-time financial fraud detection pipeline built around CockroachDB and AWS services.The article explains how historical transaction data is used to train anomaly and fraud models in Amazon SageMaker, and how Amazon Bedrock is used to generate embeddings for fraud-related transaction data.Live transactions are ingested through Amazon Kinesis Data Streams and AWS Lambda, which applies rule-based filtering, calls SageMaker model endpoints, computes similarity against historical fraudulent vectors, and writes results into CockroachDB for low-latency decisioning and monitoring.

Cockroach LabsFinance

PopChill is a pre-owned luxury item ecommerce platform in Taiwan and Hong Kong.The company uses BigQuery, Vertex AI Search for commerce, Vertex AI Vector Search, Gemini 1.5 Flash, Text embeddings API, Multimodal embeddings API, and Vertex AI Vision.It built a data warehouse from Google Analytics and Google Ads data, refreshed recommendations every two hours, enabled image search, automated policy-violation screening, product categorization, and seller ID verification.

PopChillRetail

LetsData is a Ukraine-based startup that built an AI-driven system to detect disinformation and information operations across media and social media publications.The company scans millions of publications to surface early signals of InfoOps and serves commercial and government agencies working to combat disinformation, spoofing, and synthetic identities.

Monzo, a UK digital bank, built a Google Cloud-based data analytics hub to support growth, customer insights, and fraud protection.The bank stores and models terabytes of data in BigQuery, uses Looker for rapid access to analysis, and trains ML models with Vertex AI on support/help article datasets to improve fraud protection and other predictive use cases.Monzo also runs an online 24/7 disaster recovery capability on Google Cloud that can take over within seconds, and uses the environment as a testbed for Google Kubernetes Engine.

MonzoFinance

Ravelin is a global fraud prevention company that detects fraudulent transactions online through real-time behavioural analysis, graph networks, and machine learning.Its platform takes in terabytes of historic and real-time client data through an API, runs the data through a machine learning model, and returns fraud insights to merchants through a hyperfast graph database within a 300 millisecond checkout window.Google Cloud and Cloud Key Management Service provide low-latency encryption management, autoscaling, and global deployment for the service.

RavelinFinance

UK fintech Dozens uses Google Maps Platform in its app to visualize spending insights, reduce customer support calls, and improve fraud detection.The app integrates Maps, Routes, Places, and geocoding so customers can drill into transactions, see merchant details and locations, and validate unfamiliar charges.Snowdrop Solutions’ Merchant Reconciliation System uses the Google Places database to return clean merchant names, logos, and location information, improving customer confidence and reducing anxiety around potential fraud and misuse.

DozensFinance

NatWest Group is one of the largest banks in the United Kingdom. The company uses its legacy data to innovate and personalize personal, business, corporate banking and insurance services for 20 million customers.NatWest has deployed nearly 100 machine learning models on Amazon SageMaker to drive personalized messaging and customer engagement across its banking and insurance experiences.

NatWest GroupFinance

Common questions

Fraud detection at a glance

How many fraud detection use cases are documented?
The AI Use Case Hub documents 74 real fraud detection deployments across 7 industries, with 60 detailed company examples you can browse.
Which industries adopt fraud detection the most?
Fraud detection is most common in Finance (64%), Insurance (14%) and Tech & Comms (12%).
Which countries lead in fraud detection?
United States leads documented fraud detection deployments, followed by United Kingdom and Switzerland.
What technologies are used for fraud detection?
Teams most often build fraud detection with Azure AI, Amazon SageMaker and Azure ML.
What AI capabilities power fraud detection?
Across the documented deployments, the most common capability patterns are Vision (16%), Agent (15%) and Fine-tuning (9%).
What results do companies report from fraud detection?
Across the 74 deployments reporting outcomes, companies most often cite risk & compliance (77%), customer experience & trust (73%) and speed & agility (51%). Where impact is quantified, the strongest evidence is in time & speed: a median −50% across 8 reported metrics.