HR Analytics: Using Machine Learning to Predict Employee Turnover

Matt Dancho, Founder of Business Science, presents how to use machine learning to predict employee turnover at the EARL Boston 2017 conference. He discusses two cutting edge techniques: H2O and LIME. The new H2O automated machine learning algorithm is used to get high accuracy models. The LIME package is used to explain complex deep learning models.

Code accompanying the presentation can be found in the original Business Science blog article:

Presentation materials & slides can be found at the Business Science GitHub site / presentations repo here:

Packages used: h2o, lime

Leave a Comment

Your email address will not be published. Required fields are marked *