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{194928,
        author = {J. BLESSING BOWMI and K.MANIRAJ},
        title = {Ai-Powered Intelligent Code Dependency Mapping and Automated Refactoring Recommendation System for Large-Scale Software Applications},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6635-6641},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194928},
        abstract = {As software systems grow, they become complex and difficult to maintain, leading to increased technical debt and reduced software quality. Traditional static analysis tools rely on simple rule-based techniques and often fail to detect deeper architectural issues such as circular dependencies and tightly coupled modules. To address this limitation, the proposed system introduces an AI-powered code analysis framework that combines AST parsing and graph-based dependency modeling using NetworkX to analyze complex code structures. 
The system detects code smells, duplication, and architectural flaws, and provides intelligent and context-aware refactoring suggestions. A Random Forest machine learning model evaluates code quality by generating a maintainability score and predicting refactoring risks. Additionally, an Adaptive Learning Engine improves the system over time by learning from developer feedback. By integrating graph analysis with machine learning, the system reduces manual effort, enhances decision-making, and supports safer, more efficient code maintenance, ultimately helping to control technical debt in large-scale software systems.},
        keywords = {Code Refactoring, Dependency Mapping, Code Smells, Static Code Analysis, Machine Learning.},
        month = {March},
        }