Category Archives: Blog
Scores, Models and Rules
A common approach to deploying predictive models in operational systems in which data arrives event by event is to implement an event loop: an event associated with an entity comes in, say a user (the entity) visits a page (the … Continue reading
AdReady Chooses Open Data and Augustus for their Real Time Bidding System
Augustus is a scalable Python-based open source system for building and scoring statistical and data mining models. Augustus follows the PMML standard so that models can be easily imported and exported as PMML files. Augustus 0.5.x was a rewrite of … Continue reading
How To Rapidly Prototype Analytic Models Over Big Data
Cloud computing is changing the way that companies build and deploy their analytic solutions. With cloud computing, computing is available on demand, scales elastically, and can be self-provisioned. This flexibility sometimes requires developing new analytic infrastructure and new analytic algorithms, … Continue reading