Many of the insights from Relevant Search are coming to ElasticOn! Heres what Doug will talk about:
Let’s teach a search engine some new tricks. After all a search engine thrives on comparing things–and not just text! Finding similar images, students, users, products, or weather events sound like a fancy machine learning problem. In reality we can teach a search engine to detect at risk students, predict the weather, and find similar images very efficiently and at high scale perhaps without the data scientist. In this talk we subvert search by:
- Digging in and understanding search engine internals (Solr/Elasticsearch’s)
- Learning how we can subvert this data structure to rank just about anything!
- Poking at some “stupid search tricks”– image search, student comparison, that demonstrate this subversion: turning search into a smart comparison powerhouse!