Use Case Intelligence RSS Search use cases Search
Cognizant Media and Entertainment Germany

EintrachtTech

Real-time Analytics

EintrachtTech needed to reduce queues, crowding risk and lost concession revenue at Deutsche Bank Park by understanding visitor flow at gates and kiosks in real time.

Read the original story Explore all use cases
420,000-square-meter venue
72 hours
Over 2 million annual visitors
Over 90% accuracy

Reported impact

Business outcome

EintrachtTech improved crowd management with more accurate wait-time estimates, reduced queue friction for fans, lowered operational risk in busy areas and created additional revenue potential by cutting concession abandonment.

  • Customer Experience
  • Revenue Growth
  • Risk Reduction

Solution

Cognizant acted as integration lead for EintrachtTech's visitor-flow platform at Deutsche Bank Park, using cameras and AI to estimate queues at gates and kiosks in real time. Footage from monitored areas feeds a visual sensing platform whose model calculates likely wait times rather than simply counting bodies. The deployment required repeated tuning of camera positions and model behavior so it could separate queuing from loitering, distinguish people wearing similar fan gear, and handle umbrellas and darkness on match days. Wait-time outputs are shown on screens above kiosks and can also help staff respond to congestion. Because the model follows faces to estimate flow, the pipeline was built with GDPR controls: test data was retained for 72 hours to train the models, while live data is anonymized and deleted immediately after processing. The result is an operational blend of computer-vision inference, queue analytics and privacy controls for stadium operations.

Data flow

Real-time camera footage from gates and kiosks feeds the visual sensing platform, where an AI model estimates queue lengths and wait times. The outputs are shown on screens above kiosks and can also be used to direct stadium staff toward congestion points, while privacy controls anonymize live facial metadata and delete it immediately after processing.

Solution architecture

4 components · 4 layers
  1. Ingest
    • cameras Capture real-time footage at stadium gates and kiosks for the flow-management model.
  2. Compute
    • AI model Analyzes movement patterns and estimates how long individuals will wait under different crowd conditions.
  3. Serving
    • screens above the kiosks Display predicted wait times to help visitors choose lines and help staff manage congestion.
  4. Orchestration
    • visual sensing platform Coordinates the visitor-flow solution and turns camera feeds into actionable wait-time estimates.

Architecture clues

  • Camera locations and angles were repeatedly tuned before the monitoring points were finalized.
  • Test data was retained for 72 hours for model training, while live data is deleted immediately after processing.
  • The design explicitly anonymizes facial metadata to comply with GDPR rather than performing facial recognition.
  • The model had to distinguish between people queuing and people loitering in the same area.

Evidence from the source

“After testing at multiple games, the solution achieved over 90% accuracy in predicting wait times”
“Real-time footage from cameras at gates and kiosks would feed data protection compliance into an AI model trained to analyze visitor flow.”
“The estimated waiting times calculated from this data are displayed on screens above the kiosks.”
“While test data was kept for 72 hours to train the models, live data is deleted immediately after processing, in compliance with the EU General Data Protection Regulation (GDPR).”
“up to 60,100 fans to the stadium”
Transparency Evidence & methodology 100/100 reference value · 81% confidence · 1 source

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

01

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 confidence81%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 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.
02

Traceability

Sources & provenance

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

  1. Cognizant

    EintrachtTech implements an AI-powered visitor flow management system | Cognizant

    First-party
    https://www.cognizant.com/us/en/case-studies/eintrachttech-implements-an-ai-powered-visitor-flow-management-system
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes

Date evidence

  • Sitemap last modified Aug 24, 2026 · Cognizant · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Lenovo Oct 13, 2026 Formula E Media and Entertainment global Formula E wanted fan experiences that feel immediate, immersive, personalized, and participatory, but its broadcast and event experience was limited by inconsistent onboard video quality, information spread across… Developed in under 30 days. Enterprise Knowledge SearchReal-time Analytics AI Fan Experience Guide · AI Video Optimization · AR broadcast graphics OpenAI Oct 8, 2026 Axios Media and Entertainment North America AI is already a huge part of how Axios Local works. At the core, what we’re trying to do is prove that you can run a sustainable, profitable local news model that delivers high-quality journalism to every community in… Document ProcessingReal-time Analytics Axiomizer · custom GPTs IBM Sep 14, 2026 UFC Media and Entertainment Global UFC needed a faster way to turn large volumes of performance data, historical matchups and fighter statistics into live, broadcast-ready storytelling because manual analytics workflows could not keep pace with real-time… 210+ countries airing UFC content Real-time Analytics UFC Insights Engine