• Priyanka Rajamani
• Dr.J.Savitha

The dynamic nature of real-world data streams present a significant challenge for machine learning systems, particularly in high-dimensional settings where concept drifts the change in underlying data distributions frequently occurs. This paper provides a comprehensive review of concept drift, highlighting its types, detection methods and algorithms tailored to streaming data environments. In this paper, also discuss various frameworks for processing high-dimensional data streams and explore anomaly detection methods, supervised learning techniques and adaptive algorithms designed to address drift. Key challenges, such as the curse of dimensionality, computational efficiency and delayed label availability are examined alongside future trends, including hybrid approaches and explainable AI. This study serves as a roadmap for researchers and practitioners to navigate the complexities of concept drift in high-dimensional contexts.

Concept Drift, High-Dimensional Data Streams, Data Stream Frameworks, Drift Detection Methods, Supervised Learning, Anomaly Detection and Adaptive Algorithms

"CONCEPT DRIFTS IN HIGH-DIMENSIONAL DATA STREAMS: A COMPREHENSIVE INVESTIGATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.e476-e484, December-2024, Available :http://www.jetir.org/papers/JETIR2412453.pdf

"CONCEPT DRIFTS IN HIGH-DIMENSIONAL DATA STREAMS: A COMPREHENSIVE INVESTIGATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppe476-e484, December-2024, Available at : http://www.jetir.org/papers/JETIR2412453.pdf