Imputing Missing Data using Machine Learning Modeling

Abstract: Dealing with missing data is a cornerstone of any machine learning modeling. While many methods exist, dropping, mean, median, etc, this talk will discuss a few examples were building a prediction model for missing data can increase overall model predictive strength.

Speaker: Ken Farr is Product Engineering Manager at 2nd Watch. He has a Master of Science in Computer Science from Eastern Washington University. His love of data and statistics emerged from his curiosity of discovering 'what is true'. From that he explores how to use data to drive business decisions. He flips between data science and data engineering, appreciating both sides of the field.