Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering

Sofian Kassaymeh; Gaith Rjoub; Rachida Dssouli; Jamal Bentahar; Shahed Bassam Almobydeen

doi:10.1007/978-3-031-73151-8_4

Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering

Sofian Kassaymeh
, Gaith Rjoub
, Rachida Dssouli
, Jamal Bentahar
, Shahed Bassam Almobydeen

Computer Science

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

Abstract

In order to design and develop secure and reliable software, accurate prediction of software errors is crucial. The complex, nonlinear relationship between software features and bugs that occur during development despite precautions and measures taken to prevent them makes it difficult for traditional empirical models to predict these bugs with any degree of accuracy. An integration between the Decision Tree (DT) model and the SHAP (Shapley Additive exPlanations) technique was developed in this work with the aim of predicting software faults and providing informative explanations of the expected results. The synergistic advantages of integrating DT and SHAP allow the creation of an accurate, efficient, and fully interpretable technique. In order to make the process visible and reliable, SHAP provides a global explanation of how features of the developed software affect quality and a local explanation of how features contribute to each prediction. The tendency of software features to influence software quality was revealed by feature dependence analysis.

Original language	British English
Title of host publication	The 5th Joint International Conference on AI, Big Data and Blockchain (ABB 2024)
Editors	Muhammad Younas, Irfan Awan, Natalia Kryvinska, Jamal Bentahar, Perin Ünal
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	52-66
Number of pages	15
ISBN (Print)	9783031731501
DOIs	https://doi.org/10.1007/978-3-031-73151-8_4
State	Published - 2024
Event	5th Joint International Conference on AI, Big Data and Blockchain, ABB 2024 - Vienna, Austria Duration: 19 Aug 2024 → 21 Aug 2024

Publication series

Name	Lecture Notes in Networks and Systems
Volume	881 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	5th Joint International Conference on AI, Big Data and Blockchain, ABB 2024
Country/Territory	Austria
City	Vienna
Period	19/08/24 → 21/08/24

Keywords

Decision Tree
Explainable Machine Learning
SHAP
Software Fault Prediction

Access to Document

10.1007/978-3-031-73151-8_4

Cite this

Kassaymeh, S., Rjoub, G., Dssouli, R., Bentahar, J., & Almobydeen, S. B. (2024). Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering. In M. Younas, I. Awan, N. Kryvinska, J. Bentahar, & P. Ünal (Eds.), The 5th Joint International Conference on AI, Big Data and Blockchain (ABB 2024) (pp. 52-66). (Lecture Notes in Networks and Systems; Vol. 881 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-73151-8_4

Kassaymeh, Sofian ; Rjoub, Gaith ; Dssouli, Rachida et al. / Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering. The 5th Joint International Conference on AI, Big Data and Blockchain (ABB 2024). editor / Muhammad Younas ; Irfan Awan ; Natalia Kryvinska ; Jamal Bentahar ; Perin Ünal. Springer Science and Business Media Deutschland GmbH, 2024. pp. 52-66 (Lecture Notes in Networks and Systems).

@inproceedings{0d446dd1a436411082a7909d44105f7f,

title = "Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering",

abstract = "In order to design and develop secure and reliable software, accurate prediction of software errors is crucial. The complex, nonlinear relationship between software features and bugs that occur during development despite precautions and measures taken to prevent them makes it difficult for traditional empirical models to predict these bugs with any degree of accuracy. An integration between the Decision Tree (DT) model and the SHAP (Shapley Additive exPlanations) technique was developed in this work with the aim of predicting software faults and providing informative explanations of the expected results. The synergistic advantages of integrating DT and SHAP allow the creation of an accurate, efficient, and fully interpretable technique. In order to make the process visible and reliable, SHAP provides a global explanation of how features of the developed software affect quality and a local explanation of how features contribute to each prediction. The tendency of software features to influence software quality was revealed by feature dependence analysis.",

keywords = "Decision Tree, Explainable Machine Learning, SHAP, Software Fault Prediction",

author = "Sofian Kassaymeh and Gaith Rjoub and Rachida Dssouli and Jamal Bentahar and Almobydeen, \{Shahed Bassam\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; 5th Joint International Conference on AI, Big Data and Blockchain, ABB 2024 ; Conference date: 19-08-2024 Through 21-08-2024",

year = "2024",

doi = "10.1007/978-3-031-73151-8\_4",

language = "British English",

isbn = "9783031731501",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "52--66",

editor = "Muhammad Younas and Irfan Awan and Natalia Kryvinska and Jamal Bentahar and Perin {\"U}nal",

booktitle = "The 5th Joint International Conference on AI, Big Data and Blockchain (ABB 2024)",

address = "Germany",

}

Kassaymeh, S, Rjoub, G, Dssouli, R, Bentahar, J & Almobydeen, SB 2024, Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering. in M Younas, I Awan, N Kryvinska, J Bentahar & P Ünal (eds), The 5th Joint International Conference on AI, Big Data and Blockchain (ABB 2024). Lecture Notes in Networks and Systems, vol. 881 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 52-66, 5th Joint International Conference on AI, Big Data and Blockchain, ABB 2024, Vienna, Austria, 19/08/24. https://doi.org/10.1007/978-3-031-73151-8_4

Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering. / Kassaymeh, Sofian; Rjoub, Gaith; Dssouli, Rachida et al.
The 5th Joint International Conference on AI, Big Data and Blockchain (ABB 2024). ed. / Muhammad Younas; Irfan Awan; Natalia Kryvinska; Jamal Bentahar; Perin Ünal. Springer Science and Business Media Deutschland GmbH, 2024. p. 52-66 (Lecture Notes in Networks and Systems; Vol. 881 LNNS).

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

TY - GEN

T1 - Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering

AU - Kassaymeh, Sofian

AU - Rjoub, Gaith

AU - Dssouli, Rachida

AU - Bentahar, Jamal

AU - Almobydeen, Shahed Bassam

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

PY - 2024

Y1 - 2024

N2 - In order to design and develop secure and reliable software, accurate prediction of software errors is crucial. The complex, nonlinear relationship between software features and bugs that occur during development despite precautions and measures taken to prevent them makes it difficult for traditional empirical models to predict these bugs with any degree of accuracy. An integration between the Decision Tree (DT) model and the SHAP (Shapley Additive exPlanations) technique was developed in this work with the aim of predicting software faults and providing informative explanations of the expected results. The synergistic advantages of integrating DT and SHAP allow the creation of an accurate, efficient, and fully interpretable technique. In order to make the process visible and reliable, SHAP provides a global explanation of how features of the developed software affect quality and a local explanation of how features contribute to each prediction. The tendency of software features to influence software quality was revealed by feature dependence analysis.

AB - In order to design and develop secure and reliable software, accurate prediction of software errors is crucial. The complex, nonlinear relationship between software features and bugs that occur during development despite precautions and measures taken to prevent them makes it difficult for traditional empirical models to predict these bugs with any degree of accuracy. An integration between the Decision Tree (DT) model and the SHAP (Shapley Additive exPlanations) technique was developed in this work with the aim of predicting software faults and providing informative explanations of the expected results. The synergistic advantages of integrating DT and SHAP allow the creation of an accurate, efficient, and fully interpretable technique. In order to make the process visible and reliable, SHAP provides a global explanation of how features of the developed software affect quality and a local explanation of how features contribute to each prediction. The tendency of software features to influence software quality was revealed by feature dependence analysis.

KW - Decision Tree

KW - Explainable Machine Learning

KW - SHAP

KW - Software Fault Prediction

UR - https://www.scopus.com/pages/publications/85209588951

U2 - 10.1007/978-3-031-73151-8_4

DO - 10.1007/978-3-031-73151-8_4

M3 - Conference contribution

AN - SCOPUS:85209588951

SN - 9783031731501

T3 - Lecture Notes in Networks and Systems

SP - 52

EP - 66

BT - The 5th Joint International Conference on AI, Big Data and Blockchain (ABB 2024)

A2 - Younas, Muhammad

A2 - Awan, Irfan

A2 - Kryvinska, Natalia

A2 - Bentahar, Jamal

A2 - Ünal, Perin

PB - Springer Science and Business Media Deutschland GmbH

T2 - 5th Joint International Conference on AI, Big Data and Blockchain, ABB 2024

Y2 - 19 August 2024 through 21 August 2024

ER -

Kassaymeh S, Rjoub G, Dssouli R, Bentahar J, Almobydeen SB. Interpretable SHAP-Driven Machine Learning for Accurate Fault Detection in Software Engineering. In Younas M, Awan I, Kryvinska N, Bentahar J, Ünal P, editors, The 5th Joint International Conference on AI, Big Data and Blockchain (ABB 2024). Springer Science and Business Media Deutschland GmbH. 2024. p. 52-66. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-73151-8_4