HBaseCon 2013 | Mixing Low Latency with Analytical Workloads for Customer Experience Management

Causata’s Neil Ferguson will shares the challenges they overcame getting HBase to build customer profiles from many millions of unaggregated data points per second, per server, from many TBs of data.

Date: Thursday, Jun 13 2013

Description

Causata’s event-based HBase data store has two main access patterns: low latency access (sub 50ms) to individual customer’s profiles for offer management, and streaming access to profiles matching certain query criteria, for predictive analytics. It recently migrated to HBase from its own custom-built data store, and here Neil Ferguson will share the challenges it overcame getting HBase to build customer profiles from many millions of unaggregated data points per second, per server, from many TBs of data.

Next Steps