In our capstone project we implemented unsupervised machine learning clustering methods to segment users of the real-estate website Monopolio to provide insights for marketing purposes. Our client, DD360, has a new website that presents real estate opportunities for rent and purchase in Mexico, where users can browse through different neighborhoods and cities using filters and suggestions. Users are also able to access services such as contacting a broker, applying for a mortgage or buying an appraisal for a property.
As the website started full operations in October of 2024, the client was in need of understanding who their users were and how they were browsing through the website. For this purpose, we implemented unsupervised machine learning to cluster users based on their click-data on the listings section of the website. Model selections included DBSCAN, Hierarchical Clustering and K-means, while feature engineering required data transformation and selection to implement the models.
Mentor: Greg Herschlag
