Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2015

Abstract

Resolution of problem tickets is a source of significant revenue in the worldwide software services industry. Due to the high volume of problem tickets in any large scale customer engagement, automated techniques are necessary to segregate related incoming tickets into groups. Existing techniques focus on this classification problem. In this paper, we present a case study built around the position that predicting the category of resolution times within a class of tickets and also the actual resolution times, is strongly beneficial to ticket resolution. We present an approach based on topic analysis to predict the category of resolution times of incoming tickets and validate it on a data-set of 49,000+ problem tickets across 14 classes from four real-life projects. To establish the effectiveness of our approach, we compare topic features with traditional features for both classification and regression problems. Our results indicate the promise of topic analysis based approaches for large scale problem ticket management.

Keywords

Bugs, Problem tickets, Resolution times, Service delivery, Topic analysis

Discipline

Numerical Analysis and Scientific Computing | Software Engineering

Research Areas

Information Systems and Management

Publication

ISEC '15: Proceedings of the 8th India Software Engineering Conference, February 18-20, Bengaluru

First Page

20

Last Page

29

ISBN

9781450334327

Identifier

10.1145/2723742.2723744

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/2723742.2723744

Download

Share

COinS