Recommendation Engines in Azure Machine Learning

I am working with a team of students from Imperial University on a project, one of the things they want to implement is a Recommendation engine for their new Cortana Intelligence Service. We had a interesting call today about some of their initial ideas and suggestions and I introduced them to the Azure Machine Learning Recommendations API. The recommendation engine is actually utilised by Microsoft Channel 9 online learning resource. So when you watch a video on channel 9 the recommendations are coming from a model built by this service. The model has been learning Channel 9 usage data back dated to July of 2014.