Automatic Classification of Change Requests for Improved IT Service Quality
Authors:
- Cristina KadarCKCristina Kadar
- Dorothea WiesmannDWDorothea Wiesmann
- Jose IriaJIJose Iria
- Dirk HusemannDHDirk Husemann
- Mario LucicMLMario Lucic
- 1 March 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21660778,p. 430-439
Abstract
Faulty changes to the IT infrastructure can lead to critical system and application outages, and therefore cause serious economical losses. In this paper, we describe a change planning support tool that aims at assisting the change requesters in leveraging aggregated information associated with the change, like past failure reasons or best implementation practices. The thus gained knowledge can be used in the subsequent planning and implementation steps of the change. Optimal matching of change requests with the aggregated information is achieved through the classification of the change request into about 200 fine-grained activities. We propose to automatically classify the incoming change requests using various information retrieval and machine learning techniques. The cost of building the classifiers is reduced by employing active learning techniques or by leveraging labeled features. Historical tickets from two customers were used to empirically assess and compare the accuracy of the different classification approaches (Lucene index, multinomial logistic regression, and generalized expectation criteria).Keywords
This publication has 10 references indexed in Scilit:
- Multi-dimensional Knowledge Integration for Efficient Incident Management in a Services Cloud2009
- Rule-Based Problem Classification in IT Service Management2009
- Learning from labeled features using generalized expectation criteria2008
- A Framework for Model-Based Continuous Improvement of Global IT Service Delivery Operations2008
- An approach to classify software maintenance requests2003
- Machine learning in automated text categorizationACM Computing Surveys, 2002
- Text Categorization Based on Regularized Linear Classification MethodsInformation Retrieval Journal, 2001
- A Sequential Algorithm for Training Text Classifiers1994
- A STATISTICAL INTERPRETATION OF TERM SPECIFICITY AND ITS APPLICATION IN RETRIEVALJournal of Documentation, 1972
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951