This post is the first in a series on Taste, a Java framework for providing personalized recommendations. Taste is part of the larger Mahout framework, which features various scalable machine-learning algorithms. In this post I introduce you to the concepts of personalized recommendations, also known as collaborative filtering. After this introduction, Taste’s architecture and extension points are explained. I finish this post by demonstrating and explaining the TanimotoCoefficientSimilarity, one of Taste’s implementations used for computing recommendations.
Read the rest of this entry »
Author Archive
Mahout – Taste :: Part 1 – Introduction
December 9th, 2009 by Frank Scholten(http://blog.jteam.nl/2009/12/09/mahout-taste-part-one-introduction/)
Shebang! Birth of a Groovy script
May 12th, 2009 by Frank Scholten(http://blog.jteam.nl/2009/05/12/shebang-birth-of-a-groovy-script/)
For a few days I have been browsing through Groovy in Action and wanted to give Groovy a try. So what should I code? I was busy with other stuff and while I was setting up a wicket project at home I wondered….what was the mvn wicket-quickstart syntax again?! I could have just pasted the command from the wicket site, but I decided to let Groovy handle this one. My first Groovy script was born. Read the rest of this entry »