Working with Survey Data: Semi-Supervised Learning and Biased Data
LED BY: Lukas Tencer, Senior Data Scientist, Pandora Claire Dorman, Senior Data Scientist, Pandora DESCRIPTION: This talk provides examples of how to use real-world experimental or survey data in decision making. The first step is to interpret the data correctly, which can be inherently difficult since many experiments have underlying biases. We will discuss how to deal with these biases and share tips for avoiding common mistakes when dealing with data. Furthermore, we will discuss how AI algorithms can be used to make practical decisions even when we are limited to small labeled data sets, such as data from surveys.
WHO SHOULD ATTEND: This talk will have technical elements. Familiarity with basic data analysis concepts is helpful but not necessary for learning the techniques presented.
Thursday May 31, 2018 4:30pm - 5:30pm PDT
Room 202
