Building your first recommender


You see all these websites with recommendations for things to buy or watch. During this talk Jettro walks you through all the steps to create yourself a recommender. Getting data for your recommendations from user events. Handling and enriching these user events before storing them ready to be used by the recommender. Creating a recommendation using concepts like (non) personalised recommendations, cold users, cold products and similarity algorithms L1/L2-Norm, Cosine, Pearson, k-means clustering. After this presentation you know what you need to do to get recommendations on your website.

Language: English

Level: Intermediate

Jettro Coenradie

Fellow - Luminis

I am a Software Developer / Architect with a lot of hands on experience in Java, ReactJS, Elasticsearch and lots of others tools / frameworks. I like to use these technologies to help customers with their business challenges. I have experience with importing, transforming, presenting and learning from data. Currently I am working on improving the results of search engines using learning to rank and other relevance tuning techniques. I am involved with multiple open source projects, among them is the learning-to-rank plugin for elasticsearch.

Go to speaker's detail