Large scale machine learning is playing an increasingly important role in improving the quality and monetization of Internet properties. A small number of techniques, such as regression, have proven to be widely applicable across Internet properties and applications. Sibyl is a research project that implements these primitives at scale and is widely used within Google. In this talk I will outline
![DSN 2014 Keynote: "Sibyl: A System for Large Scale Machine Learning at Google"](https://cdn-ak-scissors.b.st-hatena.com/image/square/d39566cf3ce6f5c153916d49b75e40962bf4d131/height=288;version=1;width=512/https%3A%2F%2Fi.ytimg.com%2Fvi%2FQoUVwGZb9tA%2Fhqdefault.jpg)