<![CDATA[The rapid growth of mobile banking services in Indonesia demands a deeper understanding of user behavior, especially in terms of time and transaction patterns. However, the challenge is how to effectively cluster users based on their time habits in making transactions, so that service strategies can be tailored accordingly. To address this issue, this study applies the Self-Organizing Maps (SOM) method to cluster users based on transaction time features, such as the number of transactions in the morning, afternoon, evening, night, and the division between weekdays and weekends. The dataset used includes 87,361 mobile banking users throughout 2023. The results showed that the SOM method was able to form nine different user behavior clusters, with the largest cluster being Early User (Weekday) consisting of 32,324 users (37.0%). Overall, the Early User (Weekday) segment covers about 60.3% of the user population. Meanwhile, there are also minority segments such as Night Owl (Weekday) (5.9%) and Early User (Weekend) (2.7%) that show unique behavior patterns. The model performance evaluation resulted in a Quantization Error (QE) value of 0.339 and Topographic Error (TE) of 0.066, both on validation data and test data, indicating that the clustering results are quite accurate and the data mapping topology is well maintained. This research contributes to the understanding of mobile banking user behavior segmentation and can be used as a basis for a more adaptive and personalized time-based service strategy.]]>
Copyrights © 2025
