The \(k\)-nearest neighbors algorithm is a simple, yet powerful machine learning technique used for classification and regression. The basic premise is to use closest known data points to make a prediction; for instance, if \(k = 3\), then we'd use 3 nearest neighbors of a point in the test set …

Recently I've discovered a dataset online that is a collection of 20M web queries from about 650K users over three months from March 1 to May 31 2006.

The columns are listed as follows:

• User ID - an anonymous user ID number
• Query - the query submitted by the user
• Query Time …

an interesting graph

I was going to write part two of the previous post on A/B testing now using Bayesian methods, but I plan to do that in another time since today I'm going to write about clustering, a widely used machine learning technique, specifically clustering Burger King menu …