Predicting software maintainability in object-oriented systems using ensemble techniques

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

2 Citations (Scopus)

Abstract

Prediction of the maintainability of classes in object-oriented systems is a significant factor for software success, however it is a challenging task to achieve. To date, several machine learning models have been applied with variable results and no clear indication of which techniques are more appropriate. With the goal of achieving more consistent results, this paper presents the first set of results in an extensive empirical study designed to evaluate the capability of bagging models to increase accuracy prediction over individual models. The study compares two major machine learning based approaches for predicting software maintainability: individual models (regression tree, multilayer perceptron, k-nearest neighbors and m5rules), and an ensemble model (bagging) that are applied to the QUES data set. The results obtained from this study indicate that k-nearest neighbors model outperformed all other individual models. The bagging ensemble model improved accuracy prediction significantly over almost all individual models, and the bagging ensemble models with k-nearest neighbors as a base model achieved superior accurate prediction. This paper also provides a description of the planned programme of research which aims to investigate the performance over various datasets of advanced (ensemble-based) machine learning models.
LanguageEnglish
Title of host publication2018 IEEE International Conference on Software Maintenance and Evolution
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages716-721
Number of pages6
ISBN (Print)9781538678701
DOIs
Publication statusPublished - 12 Nov 2018
Event 2018 IEEE International Conference on Software Maintenance and Evolution - Madrid, Spain
Duration: 23 Sep 201829 Sep 2019
Conference number: 34

Conference

Conference 2018 IEEE International Conference on Software Maintenance and Evolution
Abbreviated titleICSME
CountrySpain
CityMadrid
Period23/09/1829/09/19

Fingerprint

Maintainability
Learning systems
Multilayer neural networks

Keywords

  • individual models
  • bagging ensemble model
  • software maintainability
  • prediction
  • object-oriented systems

Cite this

Alsolai, H. (2018). Predicting software maintainability in object-oriented systems using ensemble techniques. In 2018 IEEE International Conference on Software Maintenance and Evolution (pp. 716-721). Piscataway, NJ: IEEE. https://doi.org/10.1109/ICSME.2018.00088
Alsolai, Hadeel. / Predicting software maintainability in object-oriented systems using ensemble techniques. 2018 IEEE International Conference on Software Maintenance and Evolution. Piscataway, NJ : IEEE, 2018. pp. 716-721
@inproceedings{c6bfa9e73a7042e78e417fc15a6abee0,
title = "Predicting software maintainability in object-oriented systems using ensemble techniques",
abstract = "Prediction of the maintainability of classes in object-oriented systems is a significant factor for software success, however it is a challenging task to achieve. To date, several machine learning models have been applied with variable results and no clear indication of which techniques are more appropriate. With the goal of achieving more consistent results, this paper presents the first set of results in an extensive empirical study designed to evaluate the capability of bagging models to increase accuracy prediction over individual models. The study compares two major machine learning based approaches for predicting software maintainability: individual models (regression tree, multilayer perceptron, k-nearest neighbors and m5rules), and an ensemble model (bagging) that are applied to the QUES data set. The results obtained from this study indicate that k-nearest neighbors model outperformed all other individual models. The bagging ensemble model improved accuracy prediction significantly over almost all individual models, and the bagging ensemble models with k-nearest neighbors as a base model achieved superior accurate prediction. This paper also provides a description of the planned programme of research which aims to investigate the performance over various datasets of advanced (ensemble-based) machine learning models.",
keywords = "individual models, bagging ensemble model, software maintainability, prediction, object-oriented systems",
author = "Hadeel Alsolai",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2018",
month = "11",
day = "12",
doi = "10.1109/ICSME.2018.00088",
language = "English",
isbn = "9781538678701",
pages = "716--721",
booktitle = "2018 IEEE International Conference on Software Maintenance and Evolution",
publisher = "IEEE",

}

Alsolai, H 2018, Predicting software maintainability in object-oriented systems using ensemble techniques. in 2018 IEEE International Conference on Software Maintenance and Evolution. IEEE, Piscataway, NJ, pp. 716-721, 2018 IEEE International Conference on Software Maintenance and Evolution , Madrid, Spain, 23/09/18. https://doi.org/10.1109/ICSME.2018.00088

Predicting software maintainability in object-oriented systems using ensemble techniques. / Alsolai, Hadeel.

2018 IEEE International Conference on Software Maintenance and Evolution. Piscataway, NJ : IEEE, 2018. p. 716-721.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Predicting software maintainability in object-oriented systems using ensemble techniques

AU - Alsolai, Hadeel

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2018/11/12

Y1 - 2018/11/12

N2 - Prediction of the maintainability of classes in object-oriented systems is a significant factor for software success, however it is a challenging task to achieve. To date, several machine learning models have been applied with variable results and no clear indication of which techniques are more appropriate. With the goal of achieving more consistent results, this paper presents the first set of results in an extensive empirical study designed to evaluate the capability of bagging models to increase accuracy prediction over individual models. The study compares two major machine learning based approaches for predicting software maintainability: individual models (regression tree, multilayer perceptron, k-nearest neighbors and m5rules), and an ensemble model (bagging) that are applied to the QUES data set. The results obtained from this study indicate that k-nearest neighbors model outperformed all other individual models. The bagging ensemble model improved accuracy prediction significantly over almost all individual models, and the bagging ensemble models with k-nearest neighbors as a base model achieved superior accurate prediction. This paper also provides a description of the planned programme of research which aims to investigate the performance over various datasets of advanced (ensemble-based) machine learning models.

AB - Prediction of the maintainability of classes in object-oriented systems is a significant factor for software success, however it is a challenging task to achieve. To date, several machine learning models have been applied with variable results and no clear indication of which techniques are more appropriate. With the goal of achieving more consistent results, this paper presents the first set of results in an extensive empirical study designed to evaluate the capability of bagging models to increase accuracy prediction over individual models. The study compares two major machine learning based approaches for predicting software maintainability: individual models (regression tree, multilayer perceptron, k-nearest neighbors and m5rules), and an ensemble model (bagging) that are applied to the QUES data set. The results obtained from this study indicate that k-nearest neighbors model outperformed all other individual models. The bagging ensemble model improved accuracy prediction significantly over almost all individual models, and the bagging ensemble models with k-nearest neighbors as a base model achieved superior accurate prediction. This paper also provides a description of the planned programme of research which aims to investigate the performance over various datasets of advanced (ensemble-based) machine learning models.

KW - individual models

KW - bagging ensemble model

KW - software maintainability

KW - prediction

KW - object-oriented systems

UR - https://icsme2018.github.io/

U2 - 10.1109/ICSME.2018.00088

DO - 10.1109/ICSME.2018.00088

M3 - Conference contribution book

SN - 9781538678701

SP - 716

EP - 721

BT - 2018 IEEE International Conference on Software Maintenance and Evolution

PB - IEEE

CY - Piscataway, NJ

ER -

Alsolai H. Predicting software maintainability in object-oriented systems using ensemble techniques. In 2018 IEEE International Conference on Software Maintenance and Evolution. Piscataway, NJ: IEEE. 2018. p. 716-721 https://doi.org/10.1109/ICSME.2018.00088