Project Info

Cal Housing

Devpost

This project did not submit a demo video on Devpost.

As a former student, I personally experienced the frustration and challenges of finding suitable housing near the campus. The scattered information, countless websites, and tedious manual searches made the process daunting. This personal experience inspired me to create "Cal Housing", a revolutionary platform to transform the way people find their housing.

Inspiration

The idea behind "Cal Housing" was born from my own struggles. I understood the pain points of students and professionals looking for housing near dynamic regions like Berkeley. I wanted to eliminate the compromise between price and distance, making the entire process more efficient, personalized, and stress-free. What I Learned My journey involved diving deep into the real estate market, understanding the nuances of different neighborhoods, and learning about the preferences and pain points of prospective renters (especially students). I also delved into the potential of advanced AI technologies to solve these problems. Building the Project Market Research: I conducted extensive market research to identify gaps in the existing housing search platforms and the unique needs of our target audience. Market Research: I conducted extensive market research to identify gaps in the existing housing search platforms and the unique needs of our target audience. AI Integration: Leveraging LLM and AI models, we integrated algorithms that could process user preferences and property data efficiently, providing tailored recommendations. AI Integration: Leveraging LLM and AI models, we integrated algorithms that could process user preferences and property data efficiently, providing tailored recommendations. User-Centric Design: We designed the platform with the user in mind, making it intuitive, easy to navigate, and highly customizable. Users can specify their budget, proximity to Berkeley, and other preferences with just a few clicks. User-Centric Design: We designed the platform with the user in mind, making it intuitive, easy to navigate, and highly customizable. Users can specify their budget, proximity to Berkeley, and other preferences with just a few clicks. Challenges Data Integration: Gathering and integrating property data from sources was a significant challenge. Ensuring the data was up-to-date and accurate required a dedicated effort. Processing the back-end and managing the data baed on user preference was also one of the challenges. Data Integration: Gathering and integrating property data from sources was a significant challenge. Ensuring the data was up-to-date and accurate required a dedicated effort. Processing the back-end and managing the data baed on user preference was also one of the challenges. Algorithm Refinement: Developing AI algorithms that could accurately predict the ideal housing options for users while considering their individual preferences and budgets was complex and required continuous refinement. Algorithm Refinement: Developing AI algorithms that could accurately predict the ideal housing options for users while considering their individual preferences and budgets was complex and required continuous refinement. Competitive Market: The real estate and housing market is highly competitive. We faced challenges in differentiating ourselves and gaining trust among users. Competitive Market: The real estate and housing market is highly competitive. We faced challenges in differentiating ourselves and gaining trust among users. Conclusion My personal experience as a student struggling to find suitable housing near the campus was the driving force behind the creation of "Cal Housing". Through dedication, innovation, and a commitment to solving the challenges of housing searches, we've built a platform that offers a streamlined, efficient, and personalized solution. Our mission is to ensure that no one has to compromise when finding their ideal home, and we're excited to continue improving and expanding our services in the future.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • JavaScriptIn code
  • Next.jsIn code
  • PythonIn code
  • ReactIn code
  • SQLIn code
  • Tailwind CSSIn code

7 of 7 appear in the indexed code.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

289 KB

Source files

50

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars