Comparing Multivariate Time Series Analysis and Machine Learning Performance for Technical Debt Prediction: The SQALE Index Case

Mikel Robredo; Nyyti Saarimäki; Rafael Peñaloza; Davide Taibi; Valentina Lenarduzzi

doi:10.1145/3644384.3644472

Comparing Multivariate Time Series Analysis and Machine Learning Performance for Technical Debt Prediction: The SQALE Index Case

Mikel Robredo
, Nyyti Saarimäki
, Rafael Peñaloza
, Davide Taibi
, Valentina Lenarduzzi

Computing Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

3 Citations (Scopus)

17 Downloads (Pure)

Abstract

Predicting Technical Debt has become a popular research niche in recent software engineering literature. However, there is no consistent approach yet that succeeds in entirely capturing the nature of this type of data. We applied each technique on a dataset consisting of the commit data of a total of 28 Java projects. We predicted the future values of the SQALE index to evaluate their predictive performance. Using these techniques we confirmed the predictive power of each of them with the same commit data. We aim to investigate further the time-dependent nature of other types of commit data to validate the existing prediction techniques.

Original language	English
Title of host publication	Proceedings of the 7th ACM/IEEE International Conference on Technical Debt (TechDebt '24)
Publisher	ACM
Pages	45-46
Number of pages	2
ISBN (Electronic)	979-8-4007-0590-8
DOIs	https://doi.org/10.1145/3644384.3644472
Publication status	Published - 2024
Publication type	A4 Article in conference proceedings
Event	ACM/IEEE International Conference on Technical Debt - Lisbon, Portugal Duration: 14 Apr 2024 → 15 Apr 2024

Conference

Conference	ACM/IEEE International Conference on Technical Debt
Country/Territory	Portugal
City	Lisbon
Period	14/04/24 → 15/04/24

Keywords

Empirical Software Engineering
Software Quality Mining Software Repositories
Technical Debt

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Safety, Risk, Reliability and Quality
Management of Technology and Innovation
Hardware and Architecture
Software

Access to Document

10.1145/3644384.3644472Licence: CC BY

3644384.3644472Final published version, 427 KBLicence: CC BY

https://urn.fi/URN:NBN:fi:tuni-202407307800Licence: CC BY

Cite this

@inproceedings{ebb2a6e41c2847d6bdebb5e76503060d,

title = "Comparing Multivariate Time Series Analysis and Machine Learning Performance for Technical Debt Prediction: The SQALE Index Case",

abstract = "Predicting Technical Debt has become a popular research niche in recent software engineering literature. However, there is no consistent approach yet that succeeds in entirely capturing the nature of this type of data. We applied each technique on a dataset consisting of the commit data of a total of 28 Java projects. We predicted the future values of the SQALE index to evaluate their predictive performance. Using these techniques we confirmed the predictive power of each of them with the same commit data. We aim to investigate further the time-dependent nature of other types of commit data to validate the existing prediction techniques.",

keywords = "Empirical Software Engineering, Software Quality Mining Software Repositories, Technical Debt",

author = "Mikel Robredo and Nyyti Saarim{\"a}ki and Rafael Pe{\~n}aloza and Davide Taibi and Valentina Lenarduzzi",

note = "Publisher Copyright: {\textcopyright} 2024 Copyright held by the owner/author(s).; ACM/IEEE International Conference on Technical Debt ; Conference date: 14-04-2024 Through 15-04-2024",

year = "2024",

doi = "10.1145/3644384.3644472",

language = "English",

pages = "45--46",

booktitle = "Proceedings of the 7th ACM/IEEE International Conference on Technical Debt (TechDebt '24)",

publisher = "ACM",

address = "United States",

}

Robredo, M, Saarimäki, N, Peñaloza, R, Taibi, D & Lenarduzzi, V 2024, Comparing Multivariate Time Series Analysis and Machine Learning Performance for Technical Debt Prediction: The SQALE Index Case. in Proceedings of the 7th ACM/IEEE International Conference on Technical Debt (TechDebt '24). ACM, pp. 45-46, ACM/IEEE International Conference on Technical Debt, Lisbon, Portugal, 14/04/24. https://doi.org/10.1145/3644384.3644472

Comparing Multivariate Time Series Analysis and Machine Learning Performance for Technical Debt Prediction: The SQALE Index Case. / Robredo, Mikel; Saarimäki, Nyyti; Peñaloza, Rafael et al.
Proceedings of the 7th ACM/IEEE International Conference on Technical Debt (TechDebt '24). ACM, 2024. p. 45-46.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Comparing Multivariate Time Series Analysis and Machine Learning Performance for Technical Debt Prediction

T2 - ACM/IEEE International Conference on Technical Debt

AU - Robredo, Mikel

AU - Saarimäki, Nyyti

AU - Peñaloza, Rafael

AU - Taibi, Davide

AU - Lenarduzzi, Valentina

PY - 2024

Y1 - 2024

N2 - Predicting Technical Debt has become a popular research niche in recent software engineering literature. However, there is no consistent approach yet that succeeds in entirely capturing the nature of this type of data. We applied each technique on a dataset consisting of the commit data of a total of 28 Java projects. We predicted the future values of the SQALE index to evaluate their predictive performance. Using these techniques we confirmed the predictive power of each of them with the same commit data. We aim to investigate further the time-dependent nature of other types of commit data to validate the existing prediction techniques.

AB - Predicting Technical Debt has become a popular research niche in recent software engineering literature. However, there is no consistent approach yet that succeeds in entirely capturing the nature of this type of data. We applied each technique on a dataset consisting of the commit data of a total of 28 Java projects. We predicted the future values of the SQALE index to evaluate their predictive performance. Using these techniques we confirmed the predictive power of each of them with the same commit data. We aim to investigate further the time-dependent nature of other types of commit data to validate the existing prediction techniques.

KW - Empirical Software Engineering

KW - Software Quality Mining Software Repositories

KW - Technical Debt

U2 - 10.1145/3644384.3644472

DO - 10.1145/3644384.3644472

M3 - Conference contribution

AN - SCOPUS:85196533523

SP - 45

EP - 46

BT - Proceedings of the 7th ACM/IEEE International Conference on Technical Debt (TechDebt '24)

PB - ACM

Y2 - 14 April 2024 through 15 April 2024

ER -

Comparing Multivariate Time Series Analysis and Machine Learning Performance for Technical Debt Prediction: The SQALE Index Case

Abstract

Conference

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this