filmov
tv
Scaling Machine Learning at Booking - Brammert Ottens - H2O AI World London 2018
Показать описание
This talk was recorded in London on October 30th, 2018.
We have a community close to 200 data scientists working on personalizing the experience of our customers, improving visibility of our partners on the platform and preventing fraud. Because of Booking’s current growth and size, tasks like finding consistent data sources, building robust features and productionizing models can be challenging and time-consuming for machine learning (ML) practitioners and the teams they work with. In this talk we will share the journey and some of the lessons learned in the machine learning services track, from the origins, where models were very much hand-crafted, till nowadays, where we have tools to discover and build reusable online and offline features, to deploy models in production quickly, and to prototype with flexibility new models and analyses. We will end by shedding some light on the road ahead, where the vision is to make all parts of the ML pipeline even more accessible and easy to use.
Bio: Brammert is a Senior Data Scientist at booking, working in the machine learning services track. Brammert has a masters in artificial intelligence and a masters in Logic from the University of Amsterdam, and a PhD in multi-agent systems from the EPFL. Prior to working at booking, he worked as a software developer at Quintiq, working on scheduling and planning algorithms. At Booking, he is working on building tooling to support its ever-growing data scientist community to become more productive.
We have a community close to 200 data scientists working on personalizing the experience of our customers, improving visibility of our partners on the platform and preventing fraud. Because of Booking’s current growth and size, tasks like finding consistent data sources, building robust features and productionizing models can be challenging and time-consuming for machine learning (ML) practitioners and the teams they work with. In this talk we will share the journey and some of the lessons learned in the machine learning services track, from the origins, where models were very much hand-crafted, till nowadays, where we have tools to discover and build reusable online and offline features, to deploy models in production quickly, and to prototype with flexibility new models and analyses. We will end by shedding some light on the road ahead, where the vision is to make all parts of the ML pipeline even more accessible and easy to use.
Bio: Brammert is a Senior Data Scientist at booking, working in the machine learning services track. Brammert has a masters in artificial intelligence and a masters in Logic from the University of Amsterdam, and a PhD in multi-agent systems from the EPFL. Prior to working at booking, he worked as a software developer at Quintiq, working on scheduling and planning algorithms. At Booking, he is working on building tooling to support its ever-growing data scientist community to become more productive.