Top stories published by Knerd in 2014

Eureka! Why You Shouldn’t Use ZooKeeper for Service Discovery

Written by Peter Kelley

Many companies use ZooKeeper for service discovery. At Knewton, we believe this is a fundamentally flawed approach. In this article, I will walk through our failures with…

3 responses

Knewton in Knerd

Sep 25, 2014

Online Cross-Validation to Predict Future Student Behavior

Written by Gizem Kucukoglu

At Knewton we use various mathematical models to understand how students learn. When building such models we want to make sure they generalize, or perform well for a large…

Knewton in Knerd

Oct 3, 2014

Offline Parameter Estimation

Written by Rishav Chakaravarti

As part of my summer internship at Knewton, I helped design and implement an offline parameter estimation batch. This blog post discusses some of the design considerations and challenges associated with the implementation…

Knewton in Knerd

Oct 3, 2014

Data Visualizations for Model Validation

Written by Daniel Sakaguchi

In order to provide students with sensible, targeted recommendations, the Knewton platform uses a variety of statistical models to track and interpret student progress. These models regularly undergo…

Knewton in Knerd

Sep 22, 2014

Kankoku: A Distributed Framework for Implementing Statistical Models

Written by Evan Shieh

As future-facing as Knewton’s adaptive learning platform may be, the concept of a personalized classroom has a surprisingly rich history. The idea has intrigued…

Knewton in Knerd

Sep 25, 2014

Making Lives Easier with Knewton Crab Stacker

Written by Brian Zeng

In a previous post, we discussed Knewton’s in-house deployment tool, Knewton Crab Stacker (KCS). To summarize, KCS is a command line tool used to make deployment of CloudFormation (one of Amazon’s…