UrbanLens

Inspiration Urban development often feels like a mystery to the people it affects most. We were inspired by the disconnect between local zoning laws and public understanding of how these laws shape housing affordability, access, and equity. With rising rent prices and growing interest in civic engagement, we wanted to create a tool that empowers both residents and policymakers with clear, data-driven insight into how zoning decisions impact our cities.

What it does UrbanLens is a web-based platform that uses machine learning to simulate the long-term effects of zoning policies on housing availability and affordability. Users can explore interactive maps, view predicted outcomes of policy changes (like mixed-use zoning or density increases), and access visualized data trends. The platform also includes a civic engagement feature that allows residents to submit feedback on proposed zoning changes, helping bridge the gap between data and decision-making.

How we built it We used Python and Scikit-learn to build the machine learning model, training it on open-source datasets that included zoning codes, housing prices, demographic data, and urban development metrics from the DMV region. The frontend was built using HTML, CSS, and JavaScript, and the interactive visualizations were created with Plotly and Leaflet.js. We integrated the model with the frontend using Flask to allow real-time simulations based on user-selected policy inputs.

Challenges we ran into The biggest challenge was finding clean, usable zoning and housing data — much of it was fragmented or inconsistent across counties. We also had to balance predictive accuracy with user-friendly simplicity, so we iterated several times on the model to avoid overcomplicating the interface. Finally, making the platform accessible to both technical and non-technical users required careful UX design and lots of feedback.

Accomplishments that we're proud of We’re proud of creating a fully functional prototype that not only runs real predictions but also encourages civic participation. It was rewarding to see a complex issue like zoning policy translated into something visual, interactive, and engaging. Winning 1st place at InnovateHacks among 50+ teams was the icing on the cake — a recognition of both our technical work and social impact focus.

What we learned We learned how deeply technical tools can empower public understanding and policymaking when paired with good design. We also gained experience with real-world data challenges, machine learning deployment, and collaborative problem-solving under time pressure. Most importantly, we saw the potential of civic tech to drive community-centered solutions.

What's next for UrbanLens We plan to expand UrbanLens by incorporating more granular data from other metropolitan areas and refining our model with more real-time housing trends. We'd also like to partner with local advocacy groups or urban planners to make the tool more accessible to communities that are directly affected by housing inequity. Eventually, we hope UrbanLens can become an open-source platform for civic education and policy modeling nationwide.