Popular searches
Not sure where to start?Talk to our team about running sovereign AI in your environment.
↑ ↓ Navigate↵ OpenEsc Close
Travelport uses H2O to retrain machine learning models in near real time, beating model decay and scoring latency across huge data volumes.
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 to 15 hours. With near real-time retraining of ML models and strong DevOps processes Travelport solved these challenges.
“Benefit of H2O is that it's really, really fast!”Levi BrackmanPrincipal Data Scientist