What challenges did Leading global food and beverage company face before AI implementation?

Competitor recipe analysis traditionally relied on expensive and time-intensive lab analyses. Analyses required a timeline of six months for results. Limited ability to benchmark against a vast number of competitors. High costs involved in traditional recipe determination methods.

What was the impact of the AI solution?

Reduced recipe analysis time from six months to hours. Achieved 80% accuracy in recipe reverse-engineering. Enabled benchmarking against 200+ competitors. Enhanced near real-time competitiveness tracking.

Source

MicrosoftWent darkEvidence: Medium60/100

Global Food Company revolutionizes recipe analysis with Azure ML

Updated Jun 13, 2026

Infosys transformed the process of competitor recipe analysis for a leading global food and beverage company using Microsoft Azure ML. Traditionally relying on time-consuming food lab analyses, Infosys employed Azure ML to reverse-engineer recipes from public data like nutrition labels. Azure Data Lake Storage and Azure Data Factories were used to process data efficiently. The solution reduced analysis timelines drastically from six months to just hours. The applied ML models achieved 80% accuracy and enabled near real-time competitor tracking, allowing the company to benchmark against 200+ competitors with unprecedented accuracy and speed. The solution is poised to disrupt food R&D globally.

Organization: Leading global food and beverage company
Industry: Consumer & Food
Location: United States
Published: November 2023

Reported outcomes

80%

accuracyQuality & accuracy

Strategic outcomes

Better decisions & insightEnabled competitor benchmarking at scaleSpeed & agilityReduced recipe analysis turnaroundCompetitive differentiationImproved competitiveness trackingNew product / capabilityReverse-engineered recipes from public data

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Accuracy: 80%

partner.microsoft.comNov 2, 2023Case studyInferred claimMedium evidence strength

Achieved 80% accuracy in recipe reverse-engineering.

Last evidence check: Jul 22, 2026

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Leading global food and beverage company
Provider: Microsoft
Maturity: Unknown
Linked source: partner.microsoft.com

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 2 of 2

1recipe reverse-engineering
2competitive intelligence

Competitor recipe analysis traditionally relied on expensive and time-intensive lab analyses.
Analyses required a timeline of six months for results.
Limited ability to benchmark against a vast number of competitors.
High costs involved in traditional recipe determination methods.

Developed machine learning models using Microsoft Azure ML to reverse-engineer recipes from public data sources.
Employed Azure Data Lake Storage for managing massive data inputs.
Utilized Azure Data Factories for seamless data integration.
Integrated market-share information for prioritizing competitor insights.

Technologies

Azure ML Azure Data Lake Storage Azure Data Factories

Reduced recipe analysis time from six months to hours.
Achieved 80% accuracy in recipe reverse-engineering.
Enabled benchmarking against 200+ competitors.
Enhanced near real-time competitiveness tracking.

Architecture

Azure ML developed and trained models to reverse-engineer recipes. Azure Data Factories enabled seamless integration of raw input data, which was stored and processed in Azure Data Lake Storage. The process was automated to allow users to trigger ML workflows through simple file drops in shared folders, reducing dependency on specialists.

Sources & evidence1

Evidence: Medium60/100Evidence strength