• Kodamasimham Krishna
• Dheerender Thakur

Real-time Automated Machine Learning (AutoML) is reshaping the landscape of data-driven decision-making by automating the end-to-end process of machine learning, from data preprocessing to model deployment, and adapting to dynamic environments. This article explores the key innovations and challenges associated with real-time AutoML systems. It discusses adaptive model training, scalable frameworks, automated pipelines, and the integration of advanced techniques such as context-aware learning and self-optimization. The paper also addresses significant challenges, including managing concept drift, ensuring data quality, handling resource constraints, achieving low latency, and addressing security and privacy concerns. By examining various case studies and applications across industries like finance, healthcare, e-commerce, and IoT, the article highlights the transformative impact of real-time AutoML. The discussion extends to future directions and emerging trends, such as edge computing, hybrid systems, explainable AI, and federated learning, emphasizing their potential to enhance the effectiveness and sustainability of real-time AutoML solutions.

Real-Time Automated Machine Learning (AutoML), Adaptive Model Training, Concept Drift, Data Preprocessing, Anomaly Detection, Edge Computing, Explainable AI

"Automated Machine Learning (AutoML) for Real-Time Data Streams: Challenges and Innovations in Online Learning Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 12, page no.f730-f739, December-2021, Available :http://www.jetir.org/papers/JETIR2112595.pdf

"Automated Machine Learning (AutoML) for Real-Time Data Streams: Challenges and Innovations in Online Learning Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 12, page no. ppf730-f739, December-2021, Available at : http://www.jetir.org/papers/JETIR2112595.pdf