@article{ART003245105},
author={Okjoo Choi},
title={D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System},
journal={Journal of Software Assessment and Valuation},
issn={2092-8114},
year={2025},
volume={21},
number={3},
pages={47-60}
TY - JOUR
AU - Okjoo Choi
TI - D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System
JO - Journal of Software Assessment and Valuation
PY - 2025
VL - 21
IS - 3
PB - Korea Software Assessment and Valuation Society
SP - 47
EP - 60
SN - 2092-8114
AB - Machine learning systems often suffer from performance degradation and reduced model reliability due to data distribution shifts (drift) that occur over time. Although various drift detection methods have been studied to address this issue, selecting a method that is well-suited to the characteristics of real-world datasets remains challenging. This study proposes the D2MR(Drift Detection Method Recommender) framework, which automatically recommends suitable detection methods based on dataset meta-features such as label availability, data type, size, dimensionality, distance computability, and distribution type. The proposed framework systematically maps data characteristics to detection methods and can be effectively integrated into drift monitoring modules of machine learning systems. Finally, the effectiveness of D2MR is validated through case studies using the CIFAR-10 image dataset and the UCI Wine Quality dataset.
KW - Data Characteristics;Drift;Drift Detection Method;Machine Learning System
DO -
UR -
ER -
Okjoo Choi. (2025). D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System. Journal of Software Assessment and Valuation, 21(3), 47-60.
Okjoo Choi. 2025, "D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System", Journal of Software Assessment and Valuation, vol.21, no.3 pp.47-60.
Okjoo Choi "D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System" Journal of Software Assessment and Valuation 21.3 pp.47-60 (2025) : 47.
Okjoo Choi. D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System. 2025; 21(3), 47-60.
Okjoo Choi. "D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System" Journal of Software Assessment and Valuation 21, no.3 (2025) : 47-60.
Okjoo Choi. D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System. Journal of Software Assessment and Valuation, 21(3), 47-60.
Okjoo Choi. D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System. Journal of Software Assessment and Valuation. 2025; 21(3) 47-60.
Okjoo Choi. D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System. 2025; 21(3), 47-60.
Okjoo Choi. "D2MR: A Framework for Recommending Drift Detection Method via Data Characteristic-based Rule Mapping in Machine Learning System" Journal of Software Assessment and Valuation 21, no.3 (2025) : 47-60.
