View a markdown version of this page

Property Optimizer for Lodging - Property Optimizer for Lodging
Property optimizer diagramFurther readingDiagram history

Property Optimizer for Lodging

Publication date: April 16, 2020 (Diagram history)

With this architecture, you can forecast lodging demand and optimize property performance. Use airline schedules, shopping data, and booking information as inputs. Generate regional and property-level forecasts with artificial intelligence and machine learning (AI/ML). The solution uses Amazon Forecast for ML-based forecasting, AWS Glue for data processing, and Amazon Quick Sight for visualization.

Property optimizer diagram

How to forecast lodging demand by using Amazon Forecast, AWS Glue, and Amazon Quick Sight.

The following steps describe the data pipeline and forecasting components for this architecture:

  1. Collect daily airline arrivals and departures at each airport from OAG schedules.

  2. Collect future airline shopping trends and booking data from sources such as Airline Reporting Corporation, 3Victors, and partner airlines.

  3. Collect future lodging shopping trends and booking data for indirect channels from sources such as STR and TravelClick.

  4. Use lodging booking engines as a source of shopping trends for direct booking.

  5. Collect property data, booking, and stay data from the central reservations system (CRS) and property management system (PMS).

  6. Use AWS Glue and Amazon EMR to discover, catalog, and process inputs. Create processed data in Amazon Simple Storage Service in Parquet format.

  7. Combine lodging and flight data to create accurate forecasts. Use Forecast to create AI/ML-based forecasting from historical recovery data.

  8. Visualize reports by using on-demand Amazon Athena and Amazon Quick Sight. For standardized recovery reports, use Amazon Redshift to create data marts.

  9. (Optional) Build a configuration dashboard with microservices. Use Amazon API Gateway, AWS Lambda, and Amazon DynamoDB to collect configuration changes and create what-if analyses.

  10. Use public datasets from AWS Data Exchange to enhance decision making.

Further reading

For additional information, see the following resources:

Diagram history

To receive updates about this reference architecture diagram, subscribe to the RSS feed.

ChangeDescriptionDate

Initial publication

Reference architecture diagram first published.

April 16, 2020

RSS subscription requirement

To subscribe to RSS updates, you must have an RSS plugin enabled for the browser you are using.