Intrinsic Indicators for Numerical Data Quality

Milen Marev, Ernesto Compatangelo, Wamberto Vasconcelos

2020

Abstract

This paper focuses on data quality indicators conceived to measure the quality of numerical datasets. We have devised a set of three different indicators, namely Intrinsic Quality, Distance-based Quality Factor and Information Entropy. The results of quality measures based on these indicators can be used in further data processing, helping to support actual data quality improvements. We argue that the proposed indicators can adequately capture in a quantitative way the impact of different numerical data quality issues including (but not limited to) gaps, noise or outliers.

Download


Paper Citation


in Harvard Style

Marev M., Compatangelo E. and Vasconcelos W. (2020). Intrinsic Indicators for Numerical Data Quality.In Proceedings of the 5th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS, ISBN 978-989-758-426-8, pages 341-348. DOI: 10.5220/0009411403410348


in Bibtex Style

@conference{iotbds20,
author={Milen Marev and Ernesto Compatangelo and Wamberto Vasconcelos},
title={Intrinsic Indicators for Numerical Data Quality},
booktitle={Proceedings of the 5th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS,},
year={2020},
pages={341-348},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009411403410348},
isbn={978-989-758-426-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS,
TI - Intrinsic Indicators for Numerical Data Quality
SN - 978-989-758-426-8
AU - Marev M.
AU - Compatangelo E.
AU - Vasconcelos W.
PY - 2020
SP - 341
EP - 348
DO - 10.5220/0009411403410348