Best Practices for Machine Learning Experimentation in Scientific Applications

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Michelucci, Umberto, Venturini, Francesca
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917107388645376
author Michelucci, Umberto
Venturini, Francesca
author_facet Michelucci, Umberto
Venturini, Francesca
contents Machine learning (ML) is increasingly adopted in scientific research, yet the quality and reliability of results often depend on how experiments are designed and documented. Poor baselines, inconsistent preprocessing, or insufficient validation can lead to misleading conclusions about model performance. This paper presents a practical and structured guide for conducting ML experiments in scientific applications, focussing on reproducibility, fair comparison, and transparent reporting. We outline a step-by-step workflow, from dataset preparation to model selection and evaluation, and propose metrics that account for overfitting and instability across validation folds, including the Logarithmic Overfitting Ratio (LOR) and the Composite Overfitting Score (COS). Through recommended practices and example reporting formats, this work aims to support researchers in establishing robust baselines and drawing valid evidence-based insights from ML models applied to scientific problems.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Best Practices for Machine Learning Experimentation in Scientific Applications
Michelucci, Umberto
Venturini, Francesca
Machine Learning
Machine learning (ML) is increasingly adopted in scientific research, yet the quality and reliability of results often depend on how experiments are designed and documented. Poor baselines, inconsistent preprocessing, or insufficient validation can lead to misleading conclusions about model performance. This paper presents a practical and structured guide for conducting ML experiments in scientific applications, focussing on reproducibility, fair comparison, and transparent reporting. We outline a step-by-step workflow, from dataset preparation to model selection and evaluation, and propose metrics that account for overfitting and instability across validation folds, including the Logarithmic Overfitting Ratio (LOR) and the Composite Overfitting Score (COS). Through recommended practices and example reporting formats, this work aims to support researchers in establishing robust baselines and drawing valid evidence-based insights from ML models applied to scientific problems.
title Best Practices for Machine Learning Experimentation in Scientific Applications
topic Machine Learning
url https://arxiv.org/abs/2511.21354