If you can't bring the data to the code, bring the code to the data.
Every 50 milliseconds (less than one-third of a blink of a human eye) a shopper interacts with a RichRelevance personalized recommendation across a network of 100+ of the world's largest retailing sites including Walmart.com, Sears.com, and Overstock.com. RichRelevance recommendations have generated over $1B in attributable sales for these mega-retailers. The algorithms that power these recommendations are created by a talented team of engineers and scientists (our founder and CEO was the former head of Amazon's Personalization R&D Department and our Chief Scientist was the principal engineer on Amazon.com's personalization strategy).
Given all we know about the pace of eCommerce, we recognize new ideas and innovations are derived from different perspectives. That is why we launched RecLab-a project designed to enable researchers outside of RichRelevance to code and run a variety of recommendation algorithms against live shopping traffic on major eCommerce sites. For the first time in eCommerce history, researchers will be given the opportunity to dynamically test and validate their recommendation algorithms in the live e-commerce environment.
How do we do this? Simple. RecLab solves the intractable problem of supplying real data to researchers by turning it on is head. Rather than attempt the impossible task of bringing sensitive, proprietary retail data to innovative code, RecLab brings the code to the data on live retailing sites. This is done via the RichRelevance cloud environment-a large-scale, distributed environment that is the backbone of the leading dynamic personalization technology solution for the web's top retailers.
The RecLab open-source project does not include any real data, obfuscated or not.
In order to facilitate testing of new algorithms, the RecLab project provides a number of synthetic data sets. It is important to note that when we say synthetic, we mean it. These data sets are not obfuscated data from real sites. They may share certain statistical properties with real data sets, but they are not real. The browsing, searching, and shopping behavior they portray never really happened on any site anywhere. So please, invest your time in using them to make sure your code works, but don't waste your time trying to map them to any real people or real shopping behavior. The shoppers they portray do not exist.