PreXP: Enhancing Trust in Data Preprocessing Through Explainability

Sandra Samuel, Nada Sharaf

2025

Abstract

Data preprocessing is a crucial yet often opaque stage in machine learning workflows. Manual preprocessing is time consuming and inconsistent, while automated pipelines efficiently transform data but lack explainabil-ity, making it difficult to track modifications and understand preprocessing decisions. This lack of transparency can lead to uncertainty and reduced confidence in data preparation. PreXP (Preprocessing with Explainabil-ity) addresses this gap by enhancing transparency in preprocessing workflows. Rather than modifying data, PreXP provides interpretability by documenting and clarifying preprocessing steps, ensuring that users remain informed about how their data has been prepared. Initial evaluations suggest that increasing visibility into preprocessing decisions improves trust and interpretability, reinforcing the need for explainability in data driven systems and supporting the development of more accountable machine learning workflows.

Paper Citation

in Harvard Style

Samuel S. and Sharaf N. (2025). PreXP: Enhancing Trust in Data Preprocessing Through Explainability. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-758-0, SciTePress, pages 407-414. DOI: 10.5220/0013519400003967

in Bibtex Style

@conference{data25,
author={Sandra Samuel and Nada Sharaf},
title={PreXP: Enhancing Trust in Data Preprocessing Through Explainability},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2025},
pages={407-414},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013519400003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - PreXP: Enhancing Trust in Data Preprocessing Through Explainability
SN - 978-989-758-758-0
AU - Samuel S.
AU - Sharaf N.
PY - 2025
SP - 407
EP - 414
DO - 10.5220/0013519400003967
PB - SciTePress