94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Big Data
Sec. Data Science
Volume 8 - 2025 | doi: 10.3389/fdata.2025.1542483
An Oversampling-Undersampling Strategy for Large-Scale Data Linkage
Provisionally accepted
Hossein Hassani 1*
Mohammad Reza Entezarian 1 Sara Zaeimzadeh 1 Leila Marvian 2 Nadejda Komendantova 3- 1 University of Tehran, Tehran, Iran
- 2 Payame Noor University, Tehran, Tehran, Iran
- 3 International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria
Effective record linkage in big data, particularly in imbalanced datasets, is a critical yet highly challenging task due to the inherent complexity involved. This paper utilizes an oversamplingundersampling strategy to address linkage imbalances, enabling more accurate and efficient record linkage within large-scale datasets. It tries to increase the instances of the minority class and decrease the dominance of the majority classes to try to reach a more balanced dataset that can be used for training and testing. Sensitivity testing was carried out by varying the training-test ratio and degree of imbalance.
Keywords: record linkage, data linkage, Imbalanced datasets, Oversampling, Undersampling, big data
Received: 09 Dec 2024; Accepted: 21 Feb 2025.
Copyright: © 2025 Hassani, Entezarian, Zaeimzadeh, Marvian and Komendantova. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Hossein Hassani, University of Tehran, Tehran, Iran
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.