Examples of using predictive analytics within K-12 education

In this session, I will discuss several examples of how our relatively new data science team has been using machine learning and predictive analytics to uncover new insights for school districts. Through the use of techniques including decision trees, random forests, and k-means clustering, we can uncover some interesting insights about our student population - with some surprises.
Who is this presentation for?
A mix of business and technical attendees. A review of algorithms will not be covered - but a focus on the results of those algorithms and their context and implications
Prerequisite knowledge:
Basic ideas around data science including differences between supervised and unsupervised learning
What you'll learn?
Attendees will learn the types of techniques we are using in the K-12 space, and some of the challenges we face in data science

Dr. Rich Huebner is a Director of Data Science & Architecture at Houghton Mifflin Harcourt, where he works as a data scientist and mentors and coaches other data scientists and analysts. He is very passionate about using data and analytics to gain new insights for school districts and helps district leaders make better decisions about student achievement.