Title: Using data mining techniques for time estimation in software maintenance

Authors: Edilson Ferneda, Hércules Antonio Do Prado, Elizabeth d’Arrochella Teixeira, Fábio Bianchi Campos

Addresses: Graduate Program on Knowledge and IT Management, Catholic University of Brasilia, SGAN 916, Módulo B, Sala A-108, 70.790-160 Brasília, DF, Brazil ' Graduate Program on Knowledge and IT Management, Catholic University of Brasilia, SGAN 916, Módulo B, Sala A-108, 70.790-160 Brasília, DF, Brazil and Management and Strategy Secretariat, Embrapa – Brazilian Agricultural Research Corporation, Parque Estação Biológica – PqEB s/n Asa Norte, 70770-901 Brasília, DF, Brazil ' Graduate Program on Knowledge and IT Management, Catholic University of Brasilia, SGAN 916, Módulo B, Sala A-127, 70.790-160 Brasília, DF, Brazil ' Graduate Program on Knowledge and IT Management, Catholic University of Brasilia, SGAN 916, Módulo B, Sala A-127, 70.790-160 Brasília, DF, Brazil

Abstract: Measuring and estimating are fundamental activities for the success of any project. In the software maintenance realm the lack of maturity, or even a low level of interest in adopting effective maintenance techniques and related metrics, has been pointed out as an important cause for the high costs involved. In this paper, data mining techniques are applied to provide a sound estimation for the time required to accomplish a maintenance task. Based on real-world data regarding maintenance requests, some regression models are built to predict the time required for each maintenance. Data on the team skill and the maintenance characteristics are mapped into values that predict better time estimations in comparison to the one predicted by the human expert. A particular finding from this research is that the time prediction provided by a human expert works as an inductive bias that improves the overall prediction accuracy of the models.

Keywords: informal reasoning; data mining; software maintenance; metrics; time estimation; maintenance time; regression modelling; team skills; maintenance characteristics; prediction accuracy.

DOI: 10.1504/IJRIS.2011.042265

International Journal of Reasoning-based Intelligent Systems, 2011 Vol.3 No.2, pp.80 - 87

Received: 08 May 2021
Accepted: 12 May 2021

Published online: 02 Sep 2011 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article