Explore how the GUM-RTDP platform delivers real-time intelligence across industries. Each industry showcases representative Business Events, AI-scored Events, end-to-end Event Flows, and AI Use Cases — illustrating how the platform's three integrated layers work together to detect, predict, and act in real time. Examples are intentionally selective; the platform's composable architecture supports a much broader range of scenarios tailored to your organization.
Event naming is intentional — a well-named event communicates its business intent without ambiguity, eliminating misinterpretation by producers and consumers alike. Where the name alone is insufficient, a precise description in the event registry completes the contract. Naming rooted in the Common Enterprise Data Model (CEDM) ensures events reflect true business concepts rather than technical or system-centric artefacts — a foundational discipline for a governed, trustworthy event fabric."
Business Events
- flight.scheduled
- passenger.checked_in
- baggage.tagged
- boarding.completed
- flight.departed
AI Events
- flight.delay.predicted
- passenger.no_show_risk.scored
- baggage.misroute_risk.predicted
- demand.forecast.generated
- ancillary.revenue.forecasted
Event Flows
- On passenger.checked_in → inference publishes passenger.no_show_risk.scored → consumers react: overbooking mgmt. service, gate agent alert
- On baggage.tagged → inference publishes baggage.misroute_risk.predicted → consumers react: manual check service, baggage handler alert
- On boarding.completed → inference publishes flight.delay.predicted → consumers react: proactive rebooking service, crew legality checker, gate manager
AI Use Cases
- O&D and operating segment demand forecasting (dynamic pricing, crew planning)
- Predictive maintenance from sensor + flight data (minimize AOG events)
- IROPS prediction (delay propagation, crew legality, misconnects)
- Customer LTV & churn prediction (loyalty + offer personalization)
- Ancillary revenue optimization (bags, seats, upgrades) by real-time context
Business Events
- carriage.coupled
- track.occupancy.updated
- delay.reported
- train.arrived
- track.blue_flagged
AI Events
- train.delay.predicted
- track_occupancy.level.forecasted
- rollingstock.failure.predicted
- passenger.demand.forecasted
- safety_incident.risk.scored
Event Flows
- On delay.reported / train.departed → inference publishes train.arrival.predicted → consumers react: pax notification service, crew reassignment, connection manager
- On track.occupancy.updated → consumers react: signal control system, switching service, safety monitor
- On track.blue_flagged → consumers react: safety halt service, dispatcher alert, maintenance coordinator
AI Use Cases
- Train delay prediction using historical patterns, congestion, weather, & asset health
- Rolling stock predictive maintenance (wheel flats, brake wear, vibration anomalies)
- Passenger demand forecasting for timetable planning and capacity allocation
- Energy optimization (eco‑driving models, regenerative braking patterns)
- Crew optimization (fatigue risk, assignment efficiency, overtime forecasting)
Business Events
- vehicle.departed
- stop.arrived
- passenger.boarded
- fare.validated
- service.disrupted
AI Events
- ridership.demand.forecasted
- crowding.level.predicted
- vehicle.failure.predicted
- service.delay_risk.scored
- fare.evasion_risk.scored
Event Flows
- On passenger.boarded → inference publishes crowding.level.predicted → consumers react: dynamic dispatch service, passenger information system
- On service.disrupted → inference publishes train.delay.predicted → consumers react: transfer protection service, passenger notification, crew reassignment
- On fare.validated → inference publishes fare.evasion_risk.scored → consumers react: inspection alert service, enforcement dispatcher
AI Use Cases
- Ridership forecasting by route, stop, and time of day for service planning
- Crowding prediction to adjust headways or dispatch extra vehicles
- Predictive maintenance for buses, trams, and stations (doors, HVAC, batteries)
- Real‑time transfer optimization (predicting missed connections)
- Fare evasion detection using patterns from taps, gates, and historical anomalies
Business Events
- traffic_flow.updated
- parking_spot.occupied
- waste_level.measured
- air_quality.recorded
- incident.reported
AI Events
- traffic_flow.level.predicted
- parking_demand.forecasted
- waste_level.quantity.forecasted
- air_quality.level.forecasted
- incident_risk.scored
Event Flows
- On traffic_flow.updated → inference publishes trafficflow.level.predicted → consumers react: signal timing service, routing information system
- On air_quality.recorded → inference publishes airquality.level.forecasted → consumers react: public alert service, school notification, event organizer
- On incident.reported → consumers react: emergency response coordinator, fire dispatch, police dispatch, EMS dispatch
AI Use Cases
- Traffic forecasting for congestion management and signal optimization
- Parking demand prediction for dynamic pricing and routing
- Waste collection optimization (fill‑level forecasting, route planning)
- Environmental forecasting (air quality, noise, flood risk)
- Emergency response optimization (resource allocation, dispatch prediction)
Business Events
- ticket.scanned
- crowd_flow.updated
- concession.purchased
- merchandise.sold
- event.concluded
AI Events
- crowdflow.level.predicted
- concession.demand.forecasted
- merchandise.sales.forecasted
- safety_incident.risk.scored
- staffing.requirement.predicted
Event Flows
- On ticket.scanned / purchased → inference publishes crowdflow.level.predicted → consumers react: staffing reallocation service, security dispatcher
- On concession.purchased → inference publishes concession.demand.forecasted → consumers react: restocking service, inventory manager
- On crowd_flow.updated → inference publishes safety_incident.risk.scored → consumers react: security response service, venue operations
AI Use Cases
- Crowd flow prediction (ingress, egress, concourse movement)
- Dynamic staffing optimization for concessions, security, and cleaning
- Real‑time demand forecasting for concessions and merchandise
- VIP/loyalty engagement models (next‑best‑action during the event)
- Safety risk prediction (heat maps of congestion, incident likelihood)
Business Events
- account.opened
- funds.transferred
- payment.processed
- loan.approved
- fraud.detected
AI Events
- transaction.fraud_risk.scored
- loan.default_risk.scored
- customer.churn_risk.scored
- credit_limit.adjustment.recommended
- payment.failure_risk.predicted
Event Flows
- On funds.transferred → inference publishes transaction.fraud_risk.scored → consumers react: transaction hold service, compliance system, customer alert
- On payment.processed → inference publishes payment.failure_risk.predicted → consumers react: customer notification service, retry manager
- On loan.approved → consumers react: KYC/AML workflow, document generation, disbursement service
- On fraud.detected → consumers react: account freeze service, customer notification, compliance reporting
AI Use Cases
- Credit scoring
- Fraud detection
- Customer lifetime value
- Next‑best‑product
- Risk modeling
Business Events
- product.created
- inventory.level.adjusted
- cart.updated
- order.placed
- payment.authorized
- shipment.delivered
AI Events
- product.demand.forecasted
- inventory.level.predicted
- order.cancellation_risk.scored
- customer.churn_risk.scored
- shipment.delay.predicted
Event Flows
- On cart.updated → inference publishes order.cancellation_risk.scored → consumers react: cart recovery service, promotions engine
- On order.placed → inference publishes transaction.fraud_risk.scored → consumers react: hold or place order based on threshold
- On inventory.level.adjusted → consumers react: replenishment service, supplier notification, demand planner
- On payment.authorized → consumers react: shipment workflow, warehouse picker, customer notification
AI Use Cases
- Demand forecasting per SKU/store
- Price elasticity modeling
- Customer lifetime value
- Recommendation engines
- Fraud scoring
Business Events
- quote.requested
- policy.bound
- claim.filed
- claim.adjusted
- payment.disbursed
AI Events
- policy_renewal.risk.scored
- claim_fraud.risk.scored
- claim_settlement.amount.predicted
- customer.lifetime_value.predicted
- quote.conversion_probability.scored
Event Flows
- On quote.requested → inference publishes quote.conversion_probability.scored → consumers react: personalized offer service, campaign manager
- On claim.filed → inference publishes claim.fraud_risk.scored → consumers react: adjuster assignment, case mgmt., customer notification
- On claim.adjusted → inference publishes claim_settlement.amount.predicted → consumers react: auto-approval service, payment processor
- On policy.bound → consumers react: underwriting workflow, document generation, billing
AI Use Cases
- Claim severity prediction
- Fraud scoring
- Risk classification
- Loss ratio forecasting
- Customer churn prediction
Business Events
- appointment.scheduled
- patient.checked_in
- diagnosis.recorded
- medication.prescribed
- claim.submitted
AI Events
- appointment.no_show_risk.scored
- diagnosis.recommendation.generated
- patient.readmission_risk.scored
- medication.adherence_risk.predicted
- resource.utilization.forecasted
Event Flows
- On patient.checked_in → inference publishes appointment.no_show_risk.scored → consumers react: outreach service, scheduling optimizer
- On diagnosis.recorded → inference publishes patient.readmission_risk.scored → consumers react: care pathway service, resource planner
- On medication.prescribed → inference publishes medication.adherence_risk.predicted → consumers react: follow-up workflow, pharmacy notification
AI Use Cases
- Predictive triage
- No‑show prediction
- Readmission risk
- Patient flow forecasting
- Treatment recommendation support
Business Events
- content.viewed
- playback.started
- playback.interrupted
- subscription.renewed
- recommendation.served
AI Events
- content.recommendation.generated
- customer.churn_risk.scored
- engagement.level.predicted
- ad.yield.forecasted
- playback.failure_risk.predicted
Event Flows
- On playback.started → inference publishes recommendation.served → consumers react: content suggestion service, ad insertion engine
- On playback.interrupted → inference publishes playback.failure_risk.predicted → consumers react: CDN failover service, QoS monitor
- On subscription.renewed → inference publishes customer.churn_risk.scored → consumers react: loyalty offer service, account manager
AI Use Cases
- Personalized content recommendations (session‑level, real‑time)
- Churn prediction based on engagement, content patterns, and QoS signals
- Ad targeting + yield optimization using behavioral and contextual features
- Content performance forecasting (what will trend, what will drop)
- Quality‑of‑experience prediction (buffering, CDN issues, device patterns)
Business Events
- application.submitted
- case.updated
- permit.issued
- benefit.approved
- compliance_flag.raised
AI Events
- application.processing_time.predicted
- fraud.risk.scored
- benefit.eligibility.scored
- service.demand.forecasted
- compliance.risk.scored
Event Flows
- On application.submitted → inference publishes application.processing_time.predicted → consumers react: priority queue service, SLA monitor, applicant notification
- On benefit.approved → inference publishes fraud.risk.scored → consumers react: audit service, compliance reporter, payment processor
- On compliance_flag.raised → consumers react: audit workflow, legal notification, case management service
AI Use Cases
- Case processing prediction (backlogs, SLA breaches, processing times)
- Fraud detection across benefits, taxation, procurement, and identity
- Citizen service demand forecasting (call centers, digital portals, in‑person visits)
- Workforce optimization for public services (health, social, transportation)
- Policy impact modeling using historical and real‑time operational data
Business Events
- meter_reading.captured
- outage.reported
- service.restored
- usage_anomaly.detected
- work_order.dispatched
AI Events
- outage.risk.predicted
- load.demand.forecasted
- leak.risk.scored
- asset.failure.predicted
- consumption.level.forecasted
Event Flows
- On meter_reading.captured → inference publishes usage_anomaly.detected → consumers react: investigation service, customer notification, billing adjuster
- On outage.reported → inference publishes outage.risk.predicted → consumers react: crew dispatch service, customer notification, grid balancer
- On work_order.dispatched → inference publishes asset.failure.predicted → consumers react: preventive maintenance service, parts procurement
AI Use Cases
- Load forecasting (short‑term and long‑term) for grid balancing
- Predictive maintenance for transformers, pumps, valves, and pipelines
- Leak detection using pressure, flow, and anomaly patterns
- Outage prediction based on weather, asset age, and historical failures
- Demand response optimization (who to notify, when, and with what incentive)
Business Events
- extraction.started
- equipment.fault.detected
- safety_incident.reported
- ore.processed
- shipment.loaded
AI Events
- equipment.failure.predicted
- safety_incident.risk.scored
- ore.grade.predicted
- production.output.forecasted
- maintenance.schedule.optimized
Event Flows
- On equipment.fault.detected → inference publishes equipment.failure.predicted → consumers react: maintenance work order service, parts procurement
- On safety_incident.reported → inference publishes safety_incident.risk.scored → consumers react: evacuation coordinator, shutdown service, compliance reporter
- On ore.processed → inference publishes ore.grade.predicted → consumers react: processing parameter adjuster, production planner
AI Use Cases
- Ore grade prediction
- Equipment failure prediction
- Production forecasting
- Environmental risk modeling
- Worker safety scoring
Business Events
- work_order.created
- material.issued
- production.completed
- quality_check.failed
- shipment.dispatched
AI Events
- equipment.failure.predicted
- safety_incident.risk.scored
- ore.grade.predicted
- production.output.forecasted
- maintenance.schedule.optimized
Event Flows
- On quality_check.failed → inference publishes quality.issue_risk.scored → consumers react: production halt service, quality manager, supplier alert
- On material.issued → inference publishes material.consumption.forecasted → consumers react: reorder service, supply chain planner
- On production.completed → consumers react: shipment dispatcher, inventory updater, billing service
AI Use Cases
- Predictive maintenance
- Yield optimization
- Quality prediction
- Supply chain forecasting
- Energy optimization
Business Events
- service.activated
- plan.changed
- usage.recorded
- outage.detected
- ticket.resolved
AI Events
- customer.churn_risk.scored
- network.outage_risk.predicted
- usage.demand.forecasted
- plan.recommendation.generated
- ticket.escalation_risk.scored
Event Flows
- On usage.recorded → inference publishes customer.churn_risk.scored → consumers react: retention offer service, account manager
- On outage.detected → inference publishes network.outage_risk.predicted → consumers react: customer notification service, field crew dispatcher
- On ticket.resolved → consumers react: satisfaction survey service, churn risk re-scorer, loyalty tracker
AI Use Cases
- Churn prediction
- Network anomaly detection
- Usage forecasting
- Next‑best‑offer
- Fraud detection
Business Events
- room.searched
- booking.created
- booking.modified
- payment.captured
- room.check_in.completed
- room.check_out.completed
AI Events
- room.demand.forecasted
- booking.cancellation_risk.scored
- guest.spend.predicted
- occupancy.rate.forecasted
- maintenance.issue.predicted
Event Flows
- On room.searched → inference publishes room.demand.forecasted → consumers react: dynamic pricing engine, inventory manager
- On booking.created → inference publishes booking.cancellation_risk.scored → consumers react: retention offer service, revenue manager
- On room.check_in.completed → consumers react: personalized offer service, housekeeping scheduler, loyalty tracker
AI Use Cases
- Average Daily Rate (ADR) optimization
- Booking pace forecasting
- Guest segmentation
- Churn prediction
- Review sentiment analysis