<![CDATA[In the digital era, train ticket payment patterns are increasingly complex with the increasing use of bank payment methods. PT XYZ, as a train ticket service provider, faces challenges in understanding customer behavior based on available transaction data. The main problem in this study is how to effectively group customer data based on their transaction characteristics to support service improvement and marketing strategies. This study implements two data mining classification algorithms, namely K-Nearest Neighbors (KNN) and Naïve Bayes, to analyze train ticket payment transaction patterns. Processing is carried out through the RapidMiner application, with an approach based on historical transaction data collected and processed using Microsoft Excel. The research methodology includes the stages of data collection, preprocessing, classification modeling, and model performance evaluation based on accuracy, precision, and recall metrics. The results show that the Naïve Bayes algorithm has superior performance compared to KNN, with an accuracy of 99.10%, a precision of 99.07%, and a recall of 99.14%. This indicates that Naïve Bayes is more effective in classifying customer transaction data. Companies can implement the Naïve Bayes algorithm in internal analytics systems to support data-driven decision-making, particularly in marketing strategies and customer service personalization]]>
Copyrights © 2025
