Final Evaluation of a Real-Time Data Adaptation Tool for Automated Machine Learning
Keywords:
Real-time data adaptation, automated machine learning, concept drift, performance optimizationAbstract
This paper presents a Real-Time Data Adaptation Tool designed to enhance the performance, stability, and automation of machine learning systems operating under continuously evolving data conditions. The proposed framework integrates automated preprocessing, concept drift detection, noise reduction, and dynamic hyperparameter optimization to maintain high model accuracy in real-time environments. Simulation results demonstrate that the tool achieves a significant 14–18% improvement in model performance, reduces latency to 45–60 ms, and outperforms recent state-of-the-art methods in accuracy, efficiency, and automation. Comparative analysis further validates the tool’s capability to support continuous learning pipelines with minimal manual intervention, making it suitable for modern AI-driven applications.
Downloads
References
Bakirov, R., Fay, D., & Gabryś, B. (2021). Automated adaptation strategies for stream learning. Machine Learning, 110(6), 1429. https://doi.org/10.1007/s10994-021-05992-x
Baratchi, M., Wang, C., Limmer, S., Rijn, J. N. van, Hoos, H. H., Bäck, T., & Olhofer, M. (2024). Automated machine learning: past, present and future. Artificial Intelligence Review, 57(5). https://doi.org/10.1007/s10462-024-10726-1
Çelik, B., Singh, P., & Vanschoren, J. (2022). Online AutoML: an adaptive AutoML framework for online learning. Machine Learning, 112(6), 1897. https://doi.org/10.1007/s10994-022-06262-0
Çelik, B., & Vanschoren, J. (2021). Adaptation Strategies for Automated Machine Learning on Evolving Data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(9), 3067. https://doi.org/10.1109/tpami.2021.3062900
Kulbach, C., Montiel, J., Bahri, M., Heyden, M., & Bifet, A. (2022). Evolution-Based Online Automated Machine Learning. In Lecture notes in computer science (p. 472). Springer Science+Business Media. https://doi.org/10.1007/978-3-031-05933-9_37
Madrid, J., Escalante, H. J., & Moales, E. (2018). Towards AutoML in the presence of Drift. https://doi.org/10.52591/lxai201812039
Martin, I. C., Mukherjee, S., Baimagambetov, A., Vanschoren, J., & Polatidis, N. (2025). Evolving Machine Learning: A Survey. https://doi.org/10.48550/ARXIV.2505.17902
Riess, M. (2022). Automating model management: a survey on metaheuristics for concept-drift adaptation. Journal of Data Information and Management, 4, 211. https://doi.org/10.1007/s42488-022-00075-5
Vinod, P., Balasaheb, W. S., Pandurang, Y. M., Ravindra, Y. S., & Sayyad, S. (2023). Automated Machine Learning: A Comprehensive Survey and Framework for Advancements. International Journal for Research in Applied Science and Engineering Technology, 11(11), 799. https://doi.org/10.22214/ijraset.2023.56634
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Computer Science, Engineering and Information Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
