Reflective Search Relevance Testing
Many organizations find relevance testing frustrating. Often we start consulting engagements and the first problem we have to solve is “how do we test search relevance?” In this article…
Elasticsearch Learning to Rank 1.0 RC1 Released
We reached a major milestone over the weekend! We released the first release candidate for version 1.0 of Elasticsearch Learning to Rank. While our partners Wikimedia and Snagajob are…
Optimizing User-Product Matching Marketplaces
The key to really understanding search, recommendations, and other ‘product matching’ systems is microeconomics. Say what!?!? No hear me out. In this article, I want to challenge you to…
Test Driving Elasticsearch Learning to Rank with a Linear Model
Last time, I created a simple linear model using three ranking signals. Using TMDB movie data, I came up with a naive model that computed a relevance score from…
Learning to Rank 101 — Linear Models
Many search nerds get an instinct they want to “learn the right boosts” to apply to their queries. Search often feels like whack-a-mole, and often folks say “if I…
What is Learning To Rank?
As an engineer, artificial intelligence (AI) is cool. Spaceships and science fiction cool. There has been a lot of attention around machine learning and artificial intelligence lately. Some of…
We’re Bringing Learning to Rank to Elasticsearch
It’s no secret that machine learning is revolutionizing many industries. This is equally true in search, where companies exhaust themselves capturing nuance through manually tuned search relevance. Mature search…
Semantic Search with Latent Semantic Analysis
A few years ago John Berryman and I experimented with integrating Latent Semantic Analysis (LSA) with Solr to build a semantically aware search engine. Recently I’ve polished that work…