Deep learning to intervene where it counts

How we built a feedback loop to optimize learning nudges

Marianne Sorba
Aug 14, 2018 · 5 min read
  • Her demographics (e.g., gender, age, country, employment level, education level)
  • Her on-platform behavioral data (e.g., whether the enrollment is paid, browser language, number of completed courses)
  • Course-level characteristics (e.g., domain, difficulty, rating)
  1. Alan could be randomly chosen (today with probability 90%) to potentially receive the message, but Alan is a new learner and has barely interacted with our messages. Since we don’t have sufficient data on him to make a reliable prediction, we send him the message to collect data.
  2. Alan could be randomly chosen (with same probability 90%) to potentially receive the message, and has interacted with enough ALICE messages for the model to make a reliable prediction. Then, based on data from Alan’s learner profile and his previous interactions with In-Course Help messages, the model outputs three probabilities: a) the probability that Alan clicks, “Yes, this was helpful”; b) the probability that Alan clicks, “No, this was not helpful”; c) the probability that Alan doesn’t interact with the message.

Coursera Engineering

We're changing the way the world learns! Posts from @Coursera engineers and data scientists!

Marianne Sorba

Written by

Data Science Intern @ Coursera, M.S in Data Science at Columbia University

Coursera Engineering

We're changing the way the world learns! Posts from @Coursera engineers and data scientists!