• Jimit Patel
• Meet Patel

The continuous influx of data in real-time applications necessitates advanced methodologies for data stream mining, particularly focusing on dynamic feature selection and model updating. This paper explores the application of machine learning techniques in data stream environments, aiming to address the challenges posed by the non-stationary nature of data streams. Dynamic feature selection methods, which identify relevant features in real-time, are crucial for maintaining the efficiency and accuracy of predictive models. Concurrently, model updating strategies ensure that machine learning models evolve with incoming data, adapting to changes and preserving their predictive performance. We review various approaches, including data life-aware model updating, hybrid batch-stream processing, and automated machine learning, and discuss their applications in fields such as IoT data analytics and network traffic management. By integrating these advanced techniques, this study provides a comprehensive overview of maintaining robust and accurate models in dynamic data stream environments.

Dynamic Feature Selection, Data Stream Mining, Concept Drift Detection, Real-time Data Analytics

"APPLICATION OF MACHINE LEARNING IN DATA STREAM MINING FOR DYNAMIC FEATURES SELECTION AND MODEL UPDATING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.g778-g783, July-2024, Available :http://www.jetir.org/papers/JETIR2407688.pdf

"APPLICATION OF MACHINE LEARNING IN DATA STREAM MINING FOR DYNAMIC FEATURES SELECTION AND MODEL UPDATING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. ppg778-g783, July-2024, Available at : http://www.jetir.org/papers/JETIR2407688.pdf