Designing a modular approach to meaningful personalization

Property discovery is not just about listings, it is about relevance. As user behavior evolved, the feed needed to move from a static listing surface to a more adaptive and personalized experience.

In this project, I led the experience design of a modular Feed powered by behavioral and contextual signals. My contribution focused on shaping how recommendation logic translated into meaningful user experiences, ensuring that personalization felt guided rather than overwhelming.

A key part of my role was facilitating cross-functional workshops with Engineering and Data teams to align on system architecture, scoring logic, and interaction models. These sessions helped bridge technical constraints with user-centered thinking, strengthening collaboration and accelerating decision-making. By creating shared understanding early, we were able to streamline the process and design a feed that balanced intelligence, clarity, and scalability.

Beyond interface design, this work focused on ensuring that recommendations carried real meaning for users. Behavioral signals and historical activity were not simply inputs for ranking, but foundations for understanding individual intent and context. The goal was not personalization for its own sake, but to shape a discovery experience that adapts to each user’s profile, preferences, and evolving needs, enabling relevance that feels intentional rather than algorithmic.

This case study explores how modular systems, collaborative facilitation, detailed design handoff and thoughtful personalization transformed the feed into a strategic product surface.

/ This project is under NDA. I'd be happy to share the full story during an interview!