Evaluation of Cluster Models for Creating Profiles of Home Buyers

The property industry in Indonesia is currently a dynamic and continuously evolving field, in line with rapid economic growth and urbanization. Shifts in lifestyle patterns, infrastructure development, and changes in government policies have had a significant impact on how properties are marketed in Indonesia. With a growing population and increasing purchasing power, the Indonesian property market is becoming more complex. Therefore, strategies are needed to segment consumer groups for effective marketing in the housing sector. This research will delve deeper into consumer segmentation in home selection, a technique that divides consumer diversity into distinct groups based on characteristics and behavior. By using an extensive dataset involving demographic data such as location, age, gender, occupation, and many other variables, clustering algorithms can uncover complex patterns to determine consumer segments in their home selection. The algorithms to be used for this study are K-Means clustering, the Gaussian Mixture model, and Hierarchical clustering. By using these three data clustering models, we can determine which algorithm produces the most ideal results for customer profiling. The results demonstrate that the K-Means algorithm outperforms the others in accurately identifying distinct consumer segments, hence producing customer profiles. Therefore, customer profiling can also be used by the marketing division as a tool to aid in promotions in order to better understand their target audience, hence creating a successful marketing campaign.