Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190719,
        author = {Veena Jadhav and Dr.Prakash Devale and Dr. Rohini Jadhav and Dr. Suahs Patil},
        title = {Just-In-Time Bug Prediction Framework Using Data Analytics, Soft Computing, and Deep Kendall Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {3009-3013},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190719},
        abstract = {Just-In-Time (JIT) bug prediction improves software quality by identifying defect-prone commits at submission time, yet existing methods suffer from class imbalance, weak representation of code change semantics, high false-positive rates, and limited explainability. Motivated by these challenges, this work proposes an interpretable JIT bug prediction framework integrating data balancing, structural feature learning, and deep sequence modeling. A Density-aware Borderline Synthetic Tomek (DBST) cleanup mechanism addresses class imbalance by preserving critical boundary instances while improving class separation. An Explainable Backfit Structural Transformer captures syntactic and semantic code change structures using dependency and constituency parsing with equivariant semantic attention. Additionally, an Explainable Deep Kendall Analysis module employs a Deep Loopy Bi-LSTM to model long-term commit dependencies and rank-based correlations, reducing false positives. A global-local, model-agnostic interpretability mechanism further provides instance-level explanations. The proposed framework enhances prediction reliability, interpretability, and practical applicability in real-world software development workflows.},
        keywords = {class imbalance, explainable deep learning, Just-in-Time bug prediction, Kendall correlation, structural code analysis},
        month = {January},
        }