<![CDATA[The development of big data technology has generated huge volumes of diverse data, creating challenges in detecting anomalies that could potentially affect decision-making. This research aims to examine the application of artificial intelligence (AI) in detecting anomalies in big data systems to support faster, more accurate and effective decision-making. The approach used includes the integration of machine learning algorithms, such as classification-based detection, clustering, and deep learning, in identifying abnormal patterns in large datasets. The research method involves real-time dataset-based simulations by measuring the performance of AI models using accuracy, precision, recall, and F1-score metrics. The results show that the application of AI can significantly improve the anomaly detection capability compared to conventional methods, with an average accuracy of 92%.]]>
