Scholarlink

<p>Software defect prediction aims to identify fault-prone modules in order to optimize testing effort and reduce development costs, particularly in increasingly complex software systems. In this work, we propose a set of ten novel object-oriented metrics designed to enrich existing datasets and enhance prediction performance. An empirical evaluation was conducted on 17 PROMISE projects by integrating the proposed metrics with traditional CK/MOOD metrics and assessing their impact using several machine learning algorithms. The results show that several of the proposed metrics are statistically significant and contribute useful predictive information. In particular, when combined with CK/MOOD metrics, the proposed metrics yielded performance gains of 4.6% in AUC, 4.3% in F1-score, and 7.3% in recall, while maintaining stable precision. These findings demonstrate that the proposed metrics capture complementary aspects of software quality not fully represented by traditional metrics, leading to more accurate and robust defect prediction models. The observed improvements were further confirmed through statistical validation, supporting the complementarity of the proposed metrics with the CK/MOOD suite.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Introducing dependency, exception and encapsulation metrics for object-oriented defect prediction: Complementarity with CK/MOOD metrics through empirical machine learning and statistical validation

  • 期刊论文

  • 发表日期：

    2026年7月14日

查看全文
  • Fatma Zohra Mekahlia,
  • Mohamed Ilyes Bouguerri,
  • Zineddine Djama,
  • Rabah Chabane-Chaouche,
  • Dhouha Yousra Dris,
  • Lynda Abdoun,
  • Ahmed Taha Haouari

摘要

Software defect prediction aims to identify fault-prone modules in order to optimize testing effort and reduce development costs, particularly in increasingly complex software systems. In this work, we propose a set of ten novel object-oriented metrics designed to enrich existing datasets and enhance prediction performance. An empirical evaluation was conducted on 17 PROMISE projects by integrating the proposed metrics with traditional CK/MOOD metrics and assessing their impact using several machine learning algorithms. The results show that several of the proposed metrics are statistically significant and contribute useful predictive information. In particular, when combined with CK/MOOD metrics, the proposed metrics yielded performance gains of 4.6% in AUC, 4.3% in F1-score, and 7.3% in recall, while maintaining stable precision. These findings demonstrate that the proposed metrics capture complementary aspects of software quality not fully represented by traditional metrics, leading to more accurate and robust defect prediction models. The observed improvements were further confirmed through statistical validation, supporting the complementarity of the proposed metrics with the CK/MOOD suite.