Flight Search
Machine learning adjusts flight search results in real time as itineraries and schedules change.
Business impact
- Flight purchases — The team measures whether people bought more flights after receiving better search results.
- Average flight options shown per search — The article reports an average of 16,000 flight options shown in one Expedia.com search.
Data requirements
- Flight itineraries (tabular) — Used to keep search results current as itineraries change.
- Schedules (tabular) — Used to adapt results as flight times and availability change.
- Search result performance metrics (tabular) — Used to compare algorithm versions and assess whether better results increase purchases.
AI methods and techniques
- Machine learning — Used to adapt flight search results as itineraries and schedules change.
- Algorithm testing and tuning — Multiple versions and bias settings are compared to see which produces better result sets.
AI models and model families
Learning algorithms
Industries
Real-world evidence
1 documented case study on record.
Companies using this: Expedia.
View the full profile with evidence, implementation detail, and comparison tools
Explore full use case →
Explore full use case →