Time-series Approaches to Change-prone Class Prediction Problem

Cristiano Melo, Matheus Lima da Cruz, Antônio Martins, José Filho, Javam Machado

2020

Abstract

During the development and maintenance of a large software project, changes can occur due to bug fix, code refactoring, or new features. In this scenario, the prediction of change-prone classes can be very useful in guiding the development team since it can focus its efforts on these pieces of software to improve their quality and make them more flexible for future changes. A considerable number of related works uses machine learning techniques to predict change-prone classes based on different kinds of metrics. However, the related works use a standard data structure, in which each instance contains the metric values for a particular class in a specific release as independent variables. Thus, these works are ignoring the temporal dependencies between the instances. In this context, we propose two novel approaches, called Concatenated and Recurrent, using time-series in order to keep the temporal dependence between the instances to improve the performance of the predictive models. The Recurrent Approach works for imbalanced datasets without the need for resampling. Our results show that the Area Under the Curve (AUC) of both proposed approaches has improved in all evaluated datasets, and they can be up to 23.6% more effective than the standard approach in state-of-art.

Paper Citation

in Harvard Style

Melo C., Lima da Cruz M., Martins A., Filho J. and Machado J. (2020). Time-series Approaches to Change-prone Class Prediction Problem.In Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-989-758-423-7, pages 122-132. DOI: 10.5220/0009397101220132

in Bibtex Style

@conference{iceis20,
author={Cristiano Melo and Matheus Lima da Cruz and Antônio Martins and José Filho and Javam Machado},
title={Time-series Approaches to Change-prone Class Prediction Problem},
booktitle={Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2020},
pages={122-132},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009397101220132},
isbn={978-989-758-423-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - Time-series Approaches to Change-prone Class Prediction Problem
SN - 978-989-758-423-7
AU - Melo C.
AU - Lima da Cruz M.
AU - Martins A.
AU - Filho J.
AU - Machado J.
PY - 2020
SP - 122
EP - 132
DO - 10.5220/0009397101220132