Recommender Systems, Basics and Different Use Cases


We have two very interesting talks in this session set up for you.

Talk 1:

Recommender systems have become widely used, especially in the e-commerce industry. Recommender systems seek to find items that are most relevant to a user. Relevance has a wide array of practical applications such as product recommendations, personalized ranking of search results, and individualized loyalty programs. The focus of this talk is to provide an introduction to Recommender Systems and how to implement them. The talk will cover three types of recommenders and the advantages and disadvantages of each type. We will use H2O, an open source, distributed machine learning platform, to implement recommender models.

Megan Kurka is a Customer Data Scientist at H2O. Prior to working at H2O, she worked as a Data Scientist building products driven by machine learning for B2B customers. She has experience working with customers across multiple industries, identifying common problems, and designing robust and automated solutions.

Talk 2:

During this presentation, Guilherme De-Oliveira, data scientist at Dataiku, will walk you through a concrete implementation of a recommender system in a Dataiku DSS data flow. Using the 2011 Movie Lens dataset, Guilherme will build the machine learning components to this custom built recommender system using Spark and H2O Sparkling Water. The talk will be followed by a Q&A session. Attendees are recommended to download Dataiku DSS prior to the talk.

Guilherme De-Oliveira recently joined Dataiku as a Data Scientist. Prior to working at Dataiku, he was a fellow at the Insight Data Science program. Before his rebirth as a Data Scientist, Guilherme worked in the finance industry and earned his PhD in applied math from Rensselaer Polytechnic.