EY Software / SaaS global

Microsoft

Risk Management

Microsoft wanted to modernize corporate spend-risk monitoring because existing compliance testing was siloed across organizations, relied on random sampling and periodic reviews, and made it hard to spot anomalies quickly or manage policies consistently across its global footprint.

Read the original story Explore all use cases

data selection population of 600 anomalous transactions

reviews 100% of invoices across the enterprise

taking out more than 10,000 hours of work annually across its business

Reported impact

Business outcome

Microsoft replaced fragmented random sampling with a scalable risk-based monitoring program that reviews global spend in real time, focuses reviewers on the riskiest transactions, consolidates siloed compliance programs, and removes substantial manual effort while improving coverage and consistency.

Solution

Microsoft expanded its longstanding relationship with EY to build the Spend Risk Monitoring Modernization program around EY Virtual, a microservices-based continuous monitoring platform on Microsoft Azure Data Factory. EY configured the Spend Analytics application to ingest Microsoft's global spending transactions, test them against risk triggers and signals, and use advanced analytics, AI and machine learning to identify anomalous activity. High-risk items flow into EY Controls, which runs on Microsoft Dynamics 365 and Power Automate so review teams can investigate and report findings without manual handoffs. Power BI provides reporting back to Microsoft, while feedback loops from completed reviews are fed back into EY Virtual to improve future screening. The result is an end-to-end, automated compliance workflow that replaces fragmented sampling with real-time risk-based monitoring across territories, business units and controls.

Data flow

Transaction data from Microsoft business units is ingested through Azure Data Factory into EY Virtual, where Spend Analytics tests each record against risk triggers and machine learning signals. High-risk anomalies move into EY Controls on Dynamics 365 and Power Automate for human review, Power BI reports the results, and the completed outcomes feed back into EY Virtual to refine future screening.

Solution architecture

7 components · 4 layers

Ingest
- Microsoft Azure Data Factory Connects and ingests Microsoft's transaction data into the EY Virtual monitoring workflow.
Compute
- Spend Analytics Applies spend-focused analytics and risk logic to identify high-risk transactions for review.
Serving
- Microsoft Dynamics 365 Provides the workflow foundation used by EY Controls for processing reviewed transactions.
- Power BI Returns compliance and anomaly reporting to Microsoft in a visualized format.
Orchestration
- EY Virtual Acts as the continuous monitoring platform that ingests global spend data and runs anomaly detection for compliance risks.
- EY Controls Routes flagged anomalies into the managed workflow for investigation, review and reporting.
- Power Automate Automates handoffs and processing steps inside the anomaly-review workflow.

Architecture clues

EY Virtual is described as a microservices-based continuous monitoring platform built on Microsoft Azure Data Factory.
Machine learning outputs are fed back into EY Virtual so screening can refine itself over time.
The Spend Analytics application was customized to monitor Microsoft's spending globally.
The workflow combines anomaly detection with EY Controls on Dynamics 365, Power Automate and Power BI reporting.

Evidence from the source

"All while consolidating its existing siloed compliance programs into a single integrated process, taking out more than 10,000 hours of work annually across its business."

"EY Virtual takes in all of those transactions, tests them against all of the risk triggers and signals, and provides us very quickly with a data selection population of 600 anomalous transactions."

"EY Virtual's Azure AI-enabled testing reviews 100% of invoices across the enterprise and identifies high-risk anomalies for human review."

"EY's forensic analytics-powered continuous monitoring platform, EY Virtual, built on the Microsoft Azure stack."

"Today, Microsoft can risk-rate its global spending in a fraction of the time previously achievable."

Transparency Evidence & methodology 100/100 reference value · 85% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100

Problem clarity20/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth25/25
Rewards named components, data flow, integrations, and architecture detail.
Outcome specificity20/20
Measures whether the reported benefit is concrete rather than a generic claim.
Quantified impact25/25
2 metrics describe measurable impact.
Deployment scale10/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence85%

Source authority20/25
The main evidence is an official vendor-published customer story.
Claim traceability25/25
12 of 12 key fields link to a named source.
Direct evidence20/20
5 direct source quotes retained.
Date provenance0/10
The publication date has no documented provenance.
Source transparency10/10
1 source reference document publisher, URL, authority, retrieval, and supported fields.
Implementation specificity10/10
Rewards source-backed components, data flow, quantified impact, and a specific outcome.

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

EY
Using technology to control spending risk in a fast-moving environment | EY - Global

First-party
https://www.ey.com/en_gl/insights/tmt/using-technology-to-control-spending-risk-in-a-fastmoving-environment

Source type
Vendor-published customer story
Supports
- Customer
- Industry
- Region
- Company size
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- Business outcome
- Metrics
- Architecture
- evidence quotes

Date evidence

First archived Apr 22, 2024 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
Open date source

Similar use cases

See all like this

OpenAI Oct 14, 2026 SentinelOne Software / SaaS North America SentinelOne needed to reverse engineer sophisticated malware far faster than specialist researchers could do manually so it could investigate more samples, spot relationships across threats, and extend scarce cyber… 8 hours to reverse-engineer malware, down from 4–6 weeks Risk ManagementSecurity and Compliance OpenAI Daybreak · OpenAI models

Google Cloud Archived · Sep 25, 2026 Aldecis Software / SaaS France Aldecis needed to automate bottom-up financial analysis because CFO and FP&A teams were spending days hunting through dashboards to find the operational causes of margin and profit drift. 85% faster financial data analysis with Real-time AnalyticsRisk Management BigQuery · BigQuery ML · Cloud Run

Google Cloud Archived · Sep 17, 2026 Parsewise Software / SaaS United Kingdom For risk specialists in the financial services and insurance industries, reading can feel like a full-time job. Whether assessing an insurance claim or approving a loan, these subject matter experts must search through… 29% lower error rate than best-performing LLM on grounded-reasoning benchmark Document ProcessingRisk Management Gemini · Gemini 3.0 Flash · Gemini 3.5 Flash