Data-Driven Application Maintenance: Experience from the Trenches

In this paper we present our experience during design, development, and pilot deployments of a data-driven machine learning based application maintenance solution. We implemented a proof of concept to address a spectrum of interrelated problems encountered in application maintenance projects including duplicate incident ticket identification, assignee recommendation, theme mining, and mapping of incidents to business processes. In the context of IT services, these problems are frequently encountered, yet there is a gap in bringing automation and optimization. Despite long-standing research around mining and analysis of software repositories, such research outputs are not adopted well in practice due to the constraints these solutions impose on the users. We discuss need for designing pragmatic solutions with low barriers to adoption and addressing right level of complexity of problems with respect to underlying business constraints and nature of data.

[1]  Serge Demeyer,et al.  The Eclipse and Mozilla defect tracking dataset: A genuine dataset for mining bug information , 2013, 2013 10th Working Conference on Mining Software Repositories (MSR).

[2]  Patrick F. Reidy.  An Introduction to Latent Semantic Analysis , 2009 .

[3]  Ladan Tahvildari,et al.  Search-based duplicate defect detection: An industrial experience , 2013, 2013 10th Working Conference on Mining Software Repositories (MSR).

[4]  Christopher D. Manning,et al.  Introduction to Information Retrieval , 2010, J. Assoc. Inf. Sci. Technol..

[5]  Rozaida Ghazali,et al.  A survey on bug prioritization , 2017, Artificial Intelligence Review.

[6]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[7]  Shubhashis Sengupta,et al.  Latent semantic centrality based automated requirements prioritization , 2014, ISEC '14.

[8]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[9]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

[10]  Bernd Brügge,et al.  Bug report assignee recommendation using activity profiles , 2013, 2013 10th Working Conference on Mining Software Repositories (MSR).

[11]  Hagen Völzer,et al.  Multi-View Incident Ticket Clustering for Optimal Ticket Dispatching , 2015, KDD.

[12]  Shubhashis Sengupta,et al.  Topic Cohesion Preserving Requirements Clustering , 2016, 2016 IEEE/ACM 5th International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering (RAISE).

[13]  Keith Phalp,et al.  From Process Model to Problem Frame - A Position Paper , 2003 .

[14]  Rüdiger Zarnekow,et al.  ITIL as common practice reference model for IT service management: formal assessment and implications for practice , 2005, 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service.

[15]  Shonali Krishnaswamy,et al.  A knowledge-rich similarity measure for improving IT incident resolution process , 2010, SAC '10.