Data-Centric Refactoring: Techniques for Improving Model Quality via Codebase Changes
TL;DR
A comprehensive taxonomy of data-centric refactoring strategies is introduced, their application across ML-driven software projects is investigated, and their impact on model accuracy, robustness, maintainability, and reproducibility is evaluated.
Abstract
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.