Cross-Domain Applications of MLOps: From Healthcare to Finance
DOI:
https://doi.org/10.60087/jklst.vol2.n2.p598Keywords:
concept drift, data stream, drift detection methods, unsupervised learning, feature (interest) point selectionAbstract
In today's digital era, the significance of data cannot be overstated. It embodies the factual and numerical essence of our everyday transactions, arriving not just statically but dynamically, in the form of data streams. These streams constitute an influx of limitless, continuous, and swift information, particularly prominent in sectors like healthcare. However, navigating this torrent of data presents formidable challenges. The sheer volume, pace, and variety make processing data streams exceedingly complex. Moreover, the task of classifying data streams is compounded by the phenomenon of concept drift, where the underlying statistical characteristics of the target variable undergo unexpected changes, especially noticeable in supervised learning scenarios.Addressing these challenges head-on, our research delves into various manifestations of concept drift within healthcare data streams. We offer an overview of established statistical and machine learning techniques tailored to tackle concept drift. Furthermore, we underscore the efficacy of deep learning algorithms in detecting concept drift and elucidate the diverse healthcare datasets employed in this endeavor.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Journal of Knowledge Learning and Science Technology ISSN: 2959-6386 (online)
This work is licensed under a Creative Commons Attribution 4.0 International License.
©2024 All rights reserved by the respective authors and JKLST.