Return to page

Case Studies

Travelport: Near Real-time AI Deployment with Huge Data and Super Low Latency

Travelport Logo Travelport Logo

"Benefit of H2O is that it's really, really fast!"

Levi Brackman
Principal Data Scientist

Use Cases

Scaling ML Platform

Overview of the Challenge

This talk discusses typical machine learning challenges and solutions for (1) model decay, (2) volume of training data, (3) time series data, (4) compute necessary, (5) scoring latency, and (6) DevOps. Previously, models were accurate at first, but started decaying after only 10 – 15 hours. With near real-time retraining of ML models and strong DevOps processes Travelport solved these challenges.