Intelligent Search and Predictive Modeling Framework for Enhancing Software Reliability and Developer Productivity

Faris Sattar Hadi

doi:10.47134/jtsi.v3i1.5490

Authors

Faris Sattar Hadi University of KUFA

DOI:

https://doi.org/10.47134/jtsi.v3i1.5490

Keywords:

Intelligent Software Engineering, Automated Program Repair, Semantic Code Retrieval, Machine Learning for Code, Predictive Modeling, Human-in-the-Loop Systems

Abstract

The demand for smart automation to improve code quality, error fixing and developer efficiency has grown with the faster growth and complexity of today’s software. This work introduces the Intelligent Search and Predictive Modeling Framework (ISPMF) - an integrated data-driven framework that leverages neural predictive modeling, adaptive human-in-the-loop feedback, and semantic code retrieval to enhance software development. In order to model both syntactic and semantic relations in code, our approach adopts a hybrid Transformer–BiLSTM architecture equipped with retrieval-augmented generation (RAG), which leverages structural information brought from Abstract Syntax Trees (ASTs) and Graph Neural Networks (GNNs). ISPMF significantly improves from state-of-the-art baselines (SequenceR, CoCoNut, and GraphCodeBERT-Repair) on all the crucial metrics based on extensive experimental results conducted on real-world datasets such as Defects4J, QuixBugs and ManySStuBs4J. Our proposed approach decreased mean debugging time by 68%, and had an 83% acceptance rate from developers; it also achieved a Top-1 retrieval accuracy of 0.61, fix correctness of 89%, and compilation pass rate of 94%. This evidence confirms that the framework is scalable, robust and applicable in realistic settings. In addition, ISPMF advances explainable and human-centered AI in software engineering by combining data-driven automation with transparent, adaptive feedback along the development process. This work opens the door to future directions including multi-language repair, reinforcement learning-based adaptability, and next-generation intelligent development environments (IDEs) that seamlessly integrate predictive analytics with developer cognition.

References

A. Zeller, “Isolating Cause-Effect Chains from Computer Programs,” in Proceedings of the ACM SIGSOFT/FSE, pp. 1–10, 2002.

C. Liang, Y. Zhang, X. Wang, et al., “A Survey of Source Code Vulnerability Analysis Based on Deep Learning,” Digital Investigation / Computers & Security, 2025.

C. Niu, C. Li, V. Ng, J. Ge, L. Huang, and B. Luo, “A Survey on Pre-Trained Models of Source Code,” in Proceedings of IJCAI, 2022.

H. Eladawy, J. Guo, A. C. Jensen, E. T. Barr, and Y. Brun, “Automated Program Repair, What Is It Good For? Not Absolutely Nothing!,” in Proceedings of the IEEE/ACM International Conference on Software Engineering (ICSE), 2024.

H. Nguyen and Y. M. Jang, “Survey of Next-generation Optical Wireless Communication Technologies for 6G and Beyond 6G,” ICT Express, 2025.

H. Zhang, X. Xia, D. Lo, et al., “Deep Learning for Code Generation: A Survey,” Science China Information Sciences, 2024.

K. Huang, Z. Xu, S. Yang, H. Sun, X. Li, Z. Yan, and Y. Zhang, “A Survey on Automated Program Repair Techniques,” arXiv preprint arXiv:2303.18184, 2023.

L. Di Grazia and M. Pradel, “Code Search: A Survey of Techniques for Finding Code,” ACM Digital Library, 2023.

N. Bibi, A. Maqbool, T. Rana, F. Afzal, and A. A. Khan, “C2B: A Semantic Source Code Retrieval Model Using CodeT5 and Bi-LSTM,” Applied Sciences, 14(13):5795, 2024.

N. S. Harzevili, A. B. Belle, J. Wang, S. Wang, Z. M. Jiang, and N. Nagappan, “A Survey on Automated Software Vulnerability Detection Using Machine Learning and Deep Learning,” arXiv preprint arXiv:2306.11673, 2023.

Q. Xin, S. Mechtaev, Z. Liu, M. Monperrus, and S. P. Reiss, “Towards Practical and Useful Automated Program Repair for Real-World Debugging,” 2024.

Q. Zhang, C. Fang, Y. Ma, W. Sun, and Z. Chen, “A Survey of Learning-based Automated Program Repair,” ACM Transactions on Software Engineering and Methodology (TOSEM), 2023.

S. Dikici and T. T. Bilgin, “Advancements in Automated Program Repair: A Comprehensive Review,” Knowledge and Information Systems (KAIS), 2025.

S. K. Jabrw, “A Systematic Survey on Large Language Models for Code Generation,” ARO – The Scientific Journal of Koya University, 2025.

T. Hoang, H. K. Dam, Y. Kamei, D. Lo, and N. Ubayashi, “DeepJIT: An End-to-End Deep Learning Framework for Just-in-Time Defect Prediction,” in Proceedings of the IEEE/ACM MSR, pp. 34–45, 2019.

T. Sharma, M. Di Penta, and A. Panichella, “A Survey on Machine Learning Techniques Applied to Source Code Analysis,” Journal of Systems and Software, vol. 206, 111934, 2024.

W. E. Wong, R. Gao, Y. Li, R. Abreu, and F. Wotawa, “A Survey on Software Fault Localization,” IEEE Transactions on Software Engineering, 42(8), 707–740, 2016.

W. Gu, Z. Li, C. Gao, C. Wang, H. Zhang, Z. Xu, and M. R. Lyu, “CRaDLe: Deep Code Retrieval Based on Semantic Dependency Learning,” Neural Networks, 2021.

X. Li, D. Li, M. Zhao, W. E. Wong, and H. Li, “Learning-Based Patch Overfitting Detection: A Survey,” Journal of Internet Technology, vol. 26, no. 1, pp. 53–64, Jan. 2025.

Y. Wan, Z. Li, Z. Liu, et al., “Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit,” arXiv preprint arXiv:2401.00288, 2024.

Y. Wang, W. Wang, S. Joty, et al., “CodeT5: Identifier-Aware Unified Pre-trained Encoder–Decoder Models for Code Understanding and Generation,” in Proceedings of EMNLP, 2021.

Y. Xie, J. Lin, H. Dong, L. Zhang, and Z. Wu, “Survey of Code Search Based on Deep Learning,” arXiv preprint arXiv:2305.05959, 2023.

Z. Feng, D. Guo, D. Tang, N. Duan, X. Feng, M. Gong, L. Shou, B. Qin, T. Liu, D. Jiang, and M. Zhou, “CodeBERT: A Pre-Trained Model for Programming and Natural Languages,” Findings of EMNLP, pp. 1536–1547, 2020.

Z. Zeng, Y. Zhang, H. Zhang, et al., “Deep Just-in-Time Defect Prediction: How Far Are We?,” in Proceedings of the ACM ISSTA, pp. 382–394, 2021.