ML-Enhanced Code Refactoring Recommendations for Improving Software Maintainability

When Testing Meets Refactoring: Catalogue, Detection, and Recommendation

This paper presents a unified catalogue of test refactoring patterns derived from a mixed-method approach involving repository mining, developer surveys, and analysis of StackOverflow discussions, to establish a rigorous benchmark for evaluating future automated recommendation systems, including those driven by Large Language Models.

Enhancing Code Quality through AI-Powered Metric-Driven Refactoring: A Multi-Model Analysis

: The growing adoption of large language models (LLMs) in software engineering has introduced new opportunities but also risks in the software maintenance lifecycle. While LLMs can generate entire codebases from natural language prompts, such automatically generated or rapidly prototyped code often accumulates structural debt, making systematic refactoring increasingly urgent. This work investigates LLMs as metric-driven refactoring assistants rather than code generators. Six models (ChatGPT, Claude, Gemini, Grok, DeepSeek, and Qwen) were evaluated on two types of Java projects: three controlled applications with manually inflated structural metrics, and three real-world applications from public GitHub repositories. Using MetricsReloaded in IntelliJ IDEA, we measured four CK metrics: complexity (WMC), cohesion (LCOM), coupling (CBO), and inheritance depth (DIT). Results indicate that LLMs significantly reduce complexity and coupling, improving class simplicity and modularity. However, cohesion improvements remained limited, with LCOM proving especially elusive. Inheritance depth showed strong reductions in synthetic high-metric applications but minimal change in real projects. ChatGPT produced the most consistent and structurally stable refactoring outputs in real applications, though occasional cohesion deterioration occurred. These findings suggest that while LLMs are valuable assistants for structural improvement, their interventions require careful monitoring to avoid unintended trade-offs.

Data-Centric Refactoring: Techniques for Improving Model Quality via Codebase Changes

Machine learning systems often fail to reach optimal performance not because of inadequate model architectures, but due to poorly structured data processing pipelines hidden within the codebase. Data-centric refactoring aims to improve model quality through systematic restructuring of code elements responsible for data collection, preprocessing, transformation, validation, and feature engineering. This paper introduces a comprehensive taxonomy of data-centric refactoring strategies, investigates their application across ML-driven software projects, and evaluates their impact on model accuracy, robustness, maintainability, and reproducibility. By bridging software refactoring principles with data-centric AI practices, the proposed framework demonstrates that code-level improvements to data handling routines can yield substantial gains in model performance while reducing technical debt. Experimental results show that systematically refactoring data pipelines leads to more reliable features, reduced noise propagation, and improved generalization. The findings position data-centric refactoring as a key discipline for modern ML engineering, enabling scalable, interpretable, and production-ready models.

Deep Evolutionary Software Design Using Adaptive Intelligence for Maintainability and Refactoring

Detecting Behavioral Changes in Python Refactoring Implementations with Foundation Models

This work proposes an approach based on a foundation model oracle that analyzes git-style diffs to identify behavioral changes introduced by Python refactorings and uncovered 13 distinct bugs among the seven refactoring types studied.

Machine Learning for Code Smell Detection and Resolution

Code smells are indicative of poor software design, maintainability issues, or potential defects, and their early detection is critical for high-quality software development. Traditional detection methods rely heavily on manual inspection or rule-based static analysis, which are often time-consuming, error-prone, and limited in adaptability. This paper explores the use of machine learning techniques for automated code smell detection and resolution. By leveraging code metrics, syntactic and semantic features, and historical refactoring data, ML models can identify patterns associated with common code smells and recommend targeted resolution strategies. The proposed approach is evaluated on open-source and industrial software projects, demonstrating improvements in detection accuracy, maintainability, and developer productivity. The study highlights the potential of intelligent, data-driven approaches to enhance software quality and support continuous code improvement.