Open menu
Atom Icon

Making Data Matter

by Rachel Feltman

The Washington Post

Article excerpt

New MIT algorithm rubs shoulders with human intuition in big data analysis

The algorithm used raw datasets to make models predicting things such as when a student would be most at risk of dropping an online course, or what indicated that a customer during a sale would turn into a repeat buyer.

Our take

Predicting Student Behaviors Through Technology-Driven Intuition

In any school district or college there is a lot of data being collected, but much of it simply sits in databases on servers taking up space. Max Kanter wants to change that. He and his advisor, Kalyan Veeramachaneni, at MIT, created the Data Science Machine algorithm which, in competitions, has demonstrated the capability of closely approximately human intuition. It beat human teams at analyzing data based on intuition and shows promise for predictive analytics. Could you be making better use of your data to predict student success?

Chances are that you could. A good starting point would be creating a list based of all of the “if only we knew…” scenarios you could come up with related to the most vexing issues you face. For instance: “If only we knew which students are likely to stay the course, and which are likely to drop out.