<![CDATA[The development of online transportation services has changed the mobility patterns of society, including among students who have high activity levels. GrabBike, as one of the application-based transportation services, is widely used by students to support their activities. Differences in intensity and usage patterns require a deeper understanding of user behavior through customer segmentation. Therefore, this study aims to segment GrabBike service users among students of the Faculty of Engineering, Sultan Ageng Tirtayasa University, using the RFM model with the application of the K-Means algorithm. This study uses a quantitative survey method with data collection through an online questionnaire (Google Form). The data used is primary data from 86 respondents who are students of the Faculty of Engineering who are GrabBike users. The stages of research include data collection, data preprocessing (cleaning, RFM transformation, and standardization using Standard Scaler), application of the K-Means algorithm, and analysis of segmentation results. The optimal number of clusters was determined using the Elbow and Silhouette methods. The results of the study show that the optimal number of clusters is three. Segmentation using the K-Means algorithm produces three user segments, namely Top Class Users, Ordinary Users, and Low Users. The Top Class Users segment has the highest frequency of use and expenditure, making them potential loyal users. The Ordinary Users segment is the largest segment with moderate usage levels and has the potential to be increased through targeted marketing strategies. Meanwhile, the Low Users segment has low usage levels and requires reactivation strategies. Overall, the K-Means-based RFM approach has proven effective in grouping GrabBike users based on usage behavior and can be used as a basis for formulating more targeted online transportation service marketing strategies.]]>
