In the streaming context, k-nearest neighbor (KNN) is the most convenient batch method. A sliding window is used to determine the KNN for a new instance that is not yet classified. It normally uses the 1,000 most recent instances for the sliding window. As the sliding window slides, it handles the concept drift, too.
Lazy learning
Get Machine Learning in Java - Second Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
