Most large-scale commercial and social websites recommend options, such
as products or people to connect with, to users. Recommendation engines sort
through massive amounts of data to identify potential user preferences. This
article, the first in a two-part series, explains the ideas behind
recommendation systems and introduces you to the algorithms that power them.
In Part 2, learn about some open source recommendation engines you can put to
Part 1 of this series introduces the basic approaches and algorithms for
the construction of recommendation engines. This concluding installment
explores some open source solutions for building recommendation systems and
demonstrates the use of two of them. The author also shows how to develop a
simple clustering application in Ruby and apply it to sample data.