Metraipolis › archive › dc_e166f7d18213

On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical Study — arXiv:2609.10610

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10610
License (as archived)
CC0-1.0
Archived
2026-10-16T05:55:07.140Z
SHA-256 of the archived text
8c875d161c7eeb9045d711f69feee002899d2e1bea492cba43ed7d0a8e8af7d1
Stable URL of this page
https://metraipolis.com/documento/dc_e166f7d18213

How to cite

On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical Study — arXiv:2609.10610 — arXiv (en), https://arxiv.org/abs/2609.10610 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e166f7d18213 (Metraipolis archive dc_e166f7d18213, sha256 8c875d161c7eeb9045d711f69feee002899d2e1bea492cba43ed7d0a8e8af7d1)
BibTeX
@misc{dce166f7d18213,
  title = {On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical Study — arXiv:2609.10610},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10610},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e166f7d18213; sha256 8c875d161c7eeb9045d711f69feee002899d2e1bea492cba43ed7d0a8e8af7d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10610. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Context: Computational notebooks are the standard environment for machine learning (ML) development. Within the ML community, model performance is often the primary considered metric, and code quality is treated as a secondary concern. This prioritization relies on a largely untested assumption that code quality and ML performance are unrelated. Practitioners also reuse existing code that may come from notebooks selected through social signals (popularity, author expertise) whose reliability as quality proxies has never been assessed. Objective: We empirically investigated the relationship between code quality and ML performance in notebooks, and evaluated whether popularity and author expertise give indication on code quality or performance. Method: We conducted a large-scale empirical study of 265,363 Python notebooks submitted to Kaggle competitions. We assessed code quality with two static analysis tools: Pylint, capturing general Python code quality, and SonarQube, configured with a profile of 34 rules targeting data-science and ML-specific practices. Results: The relationship between code quality and performance depends on the notion of quality considered. General Python code quality is decoupled from ML performance, showing negligible or non-significant correlations across all observations. In contrast, ML-specific violations exhibit a consistent, small negative association with performance that persists across all observations. The popularity of a notebook does not give information on the code quality or performance. Code expertise provides no information on quality or performance, but competition expertise correlates with better performance, fewer ML-specific violations, and slightly more Python errors and refactoring violations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG).
Categorie arXiv: Software Engineering (cs.SE) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.10610 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:44:25.030Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).