Podcast: Play in new window | Download (Duration: 57:25 — 149.3MB) | Embed
From the abstract- As machine learning emerges from research to find its place in practical applications, it’s useful to know some tips for how to build a simple but powerful recommendation engine. This talk explores how to choose effective data, how to use Apache Mahout to discover the “right kind” of co-occurrence and an innovative use of search technology for implementation. With Apache Solr to deploy the recommender, you save development time and have a dependable way to deliver rapid response recommendations in a production setting. We will also take a look at the current state of Apache Mahout, which has recently released a 0.9 version and discuss some of the best ways to get involved with this open source project.