<![CDATA[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.]]>
