Senior Software/Data Engineer Hunter Kelly of Zalando’s Dublin Fashion Insights Centre presented at this week’s Clojure/Conj on how we’re using Clojure and MLib to understand fashion in a more quantitative manner. Hunter’s talk — "Using Clojure+Spark to Find All the Topics on the Interwebs"— centered on our efforts to harness data from crowd-sourced websites such as DMOZ and Common Crawl, which enables us to explore methods of categorising the web into a set of known fashion-related topics. Then we can better answer such questions as: How many fashion-related topics are there on the Internet? How closely are they related to each other, or to other non-fashion topics? Furthermore, what topic hierarchies exist in this landscape?
Zalando was honored to participate in this year’s Clojure/Conj, which took place in Philadelphia, as both presenters and sponsors. Check out Hunter’s slides from the talk (video version here):