Distributed ML on Big Data: recommender system building experience at ivi

День 1 /  / Зал 3  /  For practicing engineers

A blog post about the first version of a recommender system at ivi in 2014 is still easy to be found at habr.ru. In this talk we decided to tell about how we walked a path from a single matrix multiplying script to a Hadoop Data Lake of our own, distributed Machine Learning with Spark, offline evaluation framework in Scala and, as a result, a recommender system highly tunable to business needs.


Download presentation