Andrea Burbank
Data Scientist
location_on United States
Member since 4 years
Share
Andrea Burbank
Specialises In (based on submitted proposals)
Andrea Burbank joined Pinterest as a data scientist in 2012, building its first successful AB testing framework, dozens of data pipelines, and a culture of testing and experimentation. Prior to Pinterest, she worked as a software engineer at Bing and as a natural language scientist on ranking and relevance at Powerset, a semantic search engine acquired by Microsoft in 2008. She has a BS in physics and a BA in linguistics from Stanford University.
-
keyboard_arrow_down
Data Science as Software at Pinterest
50 Mins
Talk
Advanced
The popular conception of data science as mining nuggets of gold from oodles of unstructured data misrepresents the importance of software engineering to the success of any data science efforts. Learning to log the right things and process data efficiently is tremendously important and easily underestimated.
-
-
keyboard_arrow_down
Data Science as Software at Pinterest
50 Mins
Talk
Advanced
The popular conception of data science as mining nuggets of gold from oodles of unstructured data misrepresents the importance of software engineering to the success of any data science efforts. Learning to log the right things and process data efficiently is tremendously important and easily underestimated.
-
-
keyboard_arrow_down
Data Science as Software at Pinterest
50 Mins
Talk
Advanced
The popular conception of data science as mining nuggets of gold from oodles of unstructured data misrepresents the importance of software engineering to the success of any data science efforts. Learning to log the right things and process data efficiently is tremendously important and easily underestimated.
-
-
keyboard_arrow_down
Building a culture of experimentation at Pinterest
50 Mins
Keynote
Intermediate
A successful experimentation program consists of much more than mere randomization and measurement. How do you help stakeholders understand the right things to measure, avoid common pitfalls, and learn to rely on A/B tests as the best way to measure a new system or feature? Building a culture of experimentation and the right tools to support it is just as important as the statistics behind the comparisons themselves - and potentially much trickier to get right.
-
-
No more submissions exist.
