Archive

Posts Tagged ‘Big data’

Massive Scale Data Mining for Education

November 17, 2011 Leave a comment

Let’s say, in the near future, tens of millions of students start learning math using online computer software.  Our logs fill with a massive new data stream, millions of students doing billions of exercises, as the students work.

In these logs, we will see some students struggle with some problems, then overcome them.  Others will struggle with those same problems and fail.  There will be paths of learning in the data, some of which quickly reach mastery, others of which go off in the weeds.

via Massive Scale Data Mining for Education | blog@CACM | Communications of the ACM

Cloudera’s CEO talks about big data

November 13, 2011 Leave a comment

Nice little talk:

Hadapt – About

October 22, 2011 Leave a comment

Performance & Stability at Scale

Hadapt’s patent-pending architecture brings the latest advances in relational database research to the Apache™ Hadoop™ platform.  By leveraging the MapReduce distributed computing framework, Hadapt provides cloud-ready fault tolerance, load balancing, and data replication, ensuring consistent performance in unpredictable computing environments such as the cloud.

Virtualized environments pose unique challenges for performing complex analytics on big data. The shared environment is economical, but unpredictable fluctuations in node performance and node availability results in poor performance for long queries. Restarting nodes or restarting queries is not the answer. Hadapt’s platform utilizes a patent-pending Adaptive Query Execution™ process to automatically load balance queries in virtualized environments.

Apache Hadoop based analytic platform : Hadapt – About.