Problem Identification by Mining Trouble Tickets

IT systems of today’s enterprises are continuously monitored and managed by a team of resolvers. Any problem in the system is reported in the form of trouble-tickets. A ticket contains various details of the observed problem. However, the knowledge of the actual problem is hidden in the ticket description along with other information. Knowledge of issues helps the service providers to better plan to improve cost and quality of operations. In this paper, we address the problem of extracting the issues from ticket descriptions. We discuss various challenges in issue extraction and present algorithms to handle different scenarios. We demonstrate the effectiveness of the proposed algorithms through two realworld case-studies.