SMOTE: makin' yourself some fake minority data

Linear Digressions

• Episode: SMOTE: makin' yourself some fake minority data
• Website: Linear Digressions
• Feed URL: http://feeds.feedburner.com/udacity-linear-digressions?format=xml
• Duration: 00:14:37
• Published: 2016-06-13 05:06

Machine learning on imbalanced classes: surprisingly tricky. Many (most?) algorithms tend to just assign the majority class label to all the data and call it a day. SMOTE is an algorithm for manufacturing new minority class examples for yourself, to help your algorithm better identify them in the wild. Relevant links: https://www.jair.org/media/953/live-953-2037-jair.pdf