Expedia Migrates Ranking Models to Keras 3: 30% Faster Training, 70% Lower Latency

fchollet · x · 2026-08-12

Expedia recently transitioned its ranking models to a state-of-the-art Keras 3 setup. According to their engineering writeup, this infrastructure upgrade yielded significant performance improvements, including 30% faster training times and a 70% reduction in inference latency.

Related event: Expedia Migrates to Keras 3, Slashing Inference Latency by 70%(2 posts)→

Original post →

More from coding & agent

coding & agent channel →