A trustworthy hybrid model for transparent software defect prediction: SPAM-XAI.
PLoS One
; 19(7): e0307112, 2024.
Article
em En
| MEDLINE
| ID: mdl-38990978
ABSTRACT
Maintaining quality in software development projects is becoming very difficult because the complexity of modules in the software is growing exponentially. Software defects are the primary concern, and software defect prediction (SDP) plays a crucial role in detecting faulty modules early and planning effective testing to reduce maintenance costs. However, SDP faces challenges like imbalanced data, high-dimensional features, model overfitting, and outliers. Moreover, traditional SDP models lack transparency and interpretability, which impacts stakeholder confidence in the Software Development Life Cycle (SDLC). We propose SPAM-XAI, a hybrid model integrating novel sampling, feature selection, and eXplainable-AI (XAI) algorithms to address these challenges. The SPAM-XAI model reduces features, optimizes the model, and reduces time and space complexity, enhancing its robustness. The SPAM-XAI model exhibited improved performance after experimenting with the NASA PROMISE repository's datasets. It achieved an accuracy of 98.13% on CM1, 96.00% on PC1, and 98.65% on PC2, surpassing previous state-of-the-art and baseline models with other evaluation matrices enhancement compared to existing methods. The SPAM-XAI model increases transparency and facilitates understanding of the interaction between features and error status, enabling coherent and comprehensible predictions. This enhancement optimizes the decision-making process and enhances the model's trustworthiness in the SDLC.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Algoritmos
/
Software
Limite:
Humans
Idioma:
En
Revista:
PLoS One
Assunto da revista:
CIENCIA
/
MEDICINA
Ano de publicação:
2024
Tipo de documento:
Article
País de afiliação:
Índia