How Buzzfeed Uses Real-Time Machine Learning to Choose Their Viral Content
by: Sheila Doshi
on October 28, 2016
This talk took place at the Domino Data Science Pop-up in Los Angeles, CA on September 14, 2016.
In this presentation, Jane Kelly, Director of Data Products at Buzzfeed, talks about how the popular online media company uses real-time machine learning to inform what content to promote, before it goes viral.
http://dominodatalab.wistia.com/medias/4d36gyinru?embedType=async videoFoam=true videoWidth=640
Listen in to learn about the innovative platform Buzzfeed has developed to:
- Capture data and feed it to a centralized hub for real-time analysis;
- Support collaboration between engineers, data scientists and content creators;
- Select the right features to identify posts that should be translated into other languages;
- Balance rapid experimentation with product stability, and effectively publish their data to different consumers internally.
Slides for Jane’s presentation can be found here.
New to Domino? Consider a Guided Tour.
Watch a Demo of DominoRecent Posts
Lightning fast CPU-based image captioning pipelines with Deep Learning and Ray Everything You Need to Know about Feature Stores 5 MLOps Best Practices for Large Organizations Choosing a Data-Governance Framework for Your Organization Transformers - Self-Attention to the rescue How data science can fail faster to leap ahead N-shot and Zero-shot learning with Python A Hands-on Tutorial for Transfer Learning in Python Getting started with k-means clustering in Python Feature extraction and image classification using Deep Neural Networks and OpenCVSubscribe to the Data Science Blog
Receive data science tips and tutorials from leading Data Scientists right to your inbox.