Mining event logs with SLCT and LogHound

Abstract

With the growth of communication networks, event logs are increasing in size at a fast rate. Today, it is not uncommon to have systems that generate tens of gigabytes of log data per day. Log data are likely to contain information that deserves closer attention - such as security events - but the task of reviewing logs manually is beyond the capabilities of a human. This paper discusses data mining tools SLCT and log hound that were designed for assisting system management personnel in extracting knowledge from event logs.