Amenity Aware

Average Transit Destination (B Grade)
Superior Transit Destination (A+ Grade)
Food Desert (USDA Definition)
Landing Page

Inspiration

After consulting various online trends, we found that many Millennials and Gen Z homebuyers—especially in the northeast—prioritize homes containing greater walking accessibility. This inspired us to create Amenity Aware, a tool that helps prospective buyers, renters, and real estate agents understand the physical activity and health benefits associated with nearby amenities.

While existing metrics such as Zillow’s Walk Score provide prospective home buyers and renters with a general sense of walkability, they often lack the ability to tailor results to individual user preferences. Coming from diverse urban and suburban backgrounds, our team was curious to see how different walking habits vary across communities.

Additionally, our experimentation with AmenityAware highlighted a serious issue: the lack of critical resources, such as grocery stores, in certain communities. In many urban areas, limited access to groceries within walking or transit distance has created food deserts that harm underprivileged populations across the Northeast.

What it does

Amenity Aware combines three key calculation metrics to estimate the potential health benefits and calories burned for a given residence.

Home location analysis: Users enter a home address, and our system applies weighted scores based on environmental factors. For instance, homes on busy roads receive a lower health benefit score, while those on tree-lined streets or near parks receive higher scores.
Commute analysis: Users input their workplace location. Our algorithm then calculates expected walking minutes per week and evaluates these against WHO guidelines for physical activity.
Amenity proximity analysis: Finally, users select the amenities that matter most to them. The model increases predicted health benefits for homes surrounded by walkable amenities, and decreases them when most amenities require driving.

How we built it

We built Amenity Aware with a modern, full-stack architecture designed for performance and adaptability. The frontend was developed using Next.js, Lucide, and Tailwind CSS to create a clean and responsive interface. We also leveraged Vercel’s AI agent, V0, which allowed us to rapidly convert sample web interface ideas into functional Next.js components suited to our purpose. The backend was built with Next.js Routes, enabling efficient handling of API calls and seamless integration between multiple data sources.

To generate our predictive insights, we integrated several APIs. The Geocode API converts user-provided addresses into geographic coordinates, while the Overpass API retrieves detailed location data for nearby buildings and amenities. The Google Routes API allows us to calculate walking distances and durations, helping us analyze transit and walking segments within complex commutes. To capture environmental context, we incorporated the MassAIR API, which stores localized data to identify whether a given home’s location supports environmentally friendly and transit-oriented living. This data is processed through the Gemini API, which assigns positive or negative weights based on those environmental factors. We chose the MassAIR API specifically for its regional accuracy and its ability to reflect the diverse blend of urban and rural environments across the Northeast.

Challenges we ran into

One key challenge was calculating multimodal transit routes—specifically distinguishing walking portions from public transit segments. To solve this, we switched to the Google Routes API, which enables precise extraction of walking times within complex routes.

Accomplishments that we're proud of

We are especially proud of our ability to bring together five different APIs into one unified and cohesive product. The integration of both locally sourced (MassAIR API) and global datasets (Geocode and Overpass) allowed us to create a meaningful narrative around the concept of place-based health and accessibility.

Our team successfully blended environmental data, health analytics, and machine learning techniques to produce metrics that are easy to interpret yet grounded in robust computation. Perhaps most importantly, we built a system that transforms abstract data into practical insights, helping individuals make more informed choices about their living environments and their well-being.

What we learned

Amenity Aware provided a deep learning experience across multiple dimensions. We explored the real-world applications of vector embeddings to quantify environmental factors through positive and negative weight assignments. More broadly, we gained practical knowledge of how diverse APIs and machine learning tools can come together to analyze transit-oriented communities in a holistic way. We also became more aware of the various Generative AI tools used to build frontend and backend frameworks professionally.

What's next for Amenity Aware

1.Implement BMI tracking for more personalized health analysis. 2.Allow users to upload activity data or short videos to convert movement into estimated step counts. 3.Continue refining our predictive algorithms to improve accuracy and personalization.

https://github.com/BensonJiang1/HackURI