Real-time Analytics
IATA wanted a repeatable short-term air-travel forecasting signal to complement long-term econometric models, but needed the entire workflow to run automatically each month with richer features and no manual intervention.
Reported impact
IATA automated its short-term forecasting process, reduced reliance on manual production, and created a richer predictive signal for air-travel outlooks and internal research.
IATA uses Google Cloud to address this challenge: IATA wanted a repeatable short-term air-travel forecasting signal to complement long-term econometric models, but needed the entire workflow to run automatically each month with richer features and no manual intervention. Cloud Scheduler triggers the monthly forecasting run without manual intervention, serving as the orchestration layer. Cloud Run functions start the execution flow that publishes the orchestration message, serving as the serving layer. Pub/Sub carries the event that wakes up the forecasting pipeline, serving as the orchestration layer. Gemini Enterprise Agent Platform orchestrates the machine-learning workflow with Kubeflow, serving as the orchestration layer. Cloud Storage stores the retrieved monthly data and intermediate assets for preprocessing and training, serving as the storage layer. Secret Manager stores the credentials used to authenticate data retrieval securely, serving as the governance layer.
A monthly Cloud Scheduler trigger calls a Cloud Run function that publishes to Pub/Sub, Gemini Enterprise Agent Platform and Kubeflow orchestrate the forecasting workflow, the pipeline retrieves and stores data in Cloud Storage, and secure secrets and keys protect access during feature engineering and model retraining.
Every month, a scheduled Cloud Scheduler job is triggered, activates a Cloud Run Function, and publishes a message to Pub/Sub.
One global ML model produces approximately 5,700 bidirectional forecasts
The ML pipeline, orchestrated through Gemini Enterprise Agent Platform with Kubeflow, comes to life without a single manual step.
The pipeline is authenticated securely using credentials stored in Google Cloud Secret Manager, encrypted by Cloud KMS.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Google Cloud Sample Archived · Oct 16, 2026 Alta Alta needed a transactable Google Cloud Marketplace path for its AI and technology spend management platform without pulling its product team off core forecasting work, while also helping finance and IT leaders… Saved 125 engineering and 60 project management hours Cloud Pub/Sub · Cloud Run · Cloud SQL Google Cloud Sample Modified · Oct 9, 2026 Anthropic During large-scale training runs, traffic is highly variable—dropping to near zero during model checkpointing before bursting to millions of events per minute. Anthropic needed a serverless messaging queue that scaled… Handles peak throughput of over 1M events per second BigQuery · Bigtable · Cloud Pub/Sub Google Cloud Sample Modified · Oct 9, 2026 Central Retail Food Replaced ~2,000 monthly manual Excel reports with a single source of truth on BigQuery through Looker dashboards Central Retail Food unifies its ecosystem on Google Cloud, moving from fragmented data to conversational… Addresses 50% to 60% of customer service queries with automated chatbots built on Conversational Agents BigQuery · Gemini · Gemini platform 