<![CDATA[significant increase in the volume of customer transaction data, but its utilization as a basis for strategic decision-making remains suboptimal. Priority customers are a high-value segment that requires a deep understanding of transaction patterns to support improved service quality and loyalty. This study aims to analyze the application of data mining methods using the Naive Bayes algorithm to classify priority customer transactions at PT. CIMB Niaga into Silver, Gold, Platinum, and Black categories. The research methods used include literature review, secondary data collection in the form of priority customer transaction data, including transaction frequency, transaction type, nominal amount, and balance, requirements analysis, system design, implementation, and system testing. The dataset used consists of a number of priority customer transaction data simulated to resemble real banking conditions. The results show that the Naive Bayes algorithm is capable of classifying priority customer transactions effectively and efficiently with a sufficient level of accuracy and relatively fast computation time. The developed system is able to display classification results in a structured manner and supports analysis of customer transaction behavior. The conclusion of this study indicates that applying data mining with the Naive Bayes algorithm can be a solution to support strategic decision-making, particularly in priority customer segmentation, improving service quality, and banking operational efficiency. ]]>
Copyrights © 2026
