Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175009,
        author = {DR. DHANDAPANI PARAMASIVAM and Mr.KADIRI REDDI SEKHARA and MS. BEKKAM RAMYASREE and Mr.C. SAINATH REDDY},
        title = {REVOLUTIONIZING ANOMALY DETECTION: LEVERAGING RISK ASSESSMENT AND MACHINE LEARNING FOR IMBALANCED DATA ANALYSIS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {1845-1851},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175009},
        abstract = {Anomaly detection in imbalanced datasets remains a significant challenge in domains such as cybersecurity, healthcare, and finance, where rare but critical anomalies are often overshadowed by normal instances. Traditional machine learning models struggle with bias toward majority classes, leading to poor detection of rare events. This study proposes an advanced anomaly detection framework that integrates risk assessment with cutting-edge machine learning techniques, including SMOTE-based data augmentation, XGBoost for feature importance, LSTM for sequential anomaly detection, and variational autoencoders (VAE) for unsupervised learning. Cost-sensitive optimization and adaptive weighting mechanisms further enhance model performance. Experimental results on benchmark datasets, such as NSL-KDD and Credit Card Fraud Detection, demonstrate a significant improvement in precision and recall, reducing false negatives by 30%. The proposed approach provides a scalable, high-precision anomaly detection solution, improving reliability in critical real-world applications.},
        keywords = {Anomaly Detection, Imbalanced Data, Risk Assessment, Machine Learning, Hybrid Algorithms.},
        month = {April},
        }