ScholarBuddy

Inspiration

Finding the right scholarship is often overwhelming for students. With thousands of options spread across fragmented platforms, many deserving candidates miss out due to lack of access, clarity, or guidance. We wanted to change that. ScholarBuddy was inspired by the idea of building a smart, conversational AI assistant that helps students easily discover scholarships tailored to their unique background—in seconds.

What it does

ScholarBuddy is an AI-powered web app that intelligently matches students with scholarships based on personal criteria like country, level of study, field of interest, and family income. Through a simple chatbot interface, users input their information, and the system instantly filters and returns a curated list of eligible scholarships, including key details like amount, deadline, and application links.

How we built it

Frontend: Built with React.js, the chatbot interface collects user input in a conversational flow. Axios is used to communicate with the backend API.
Backend: A Python Flask server receives requests and processes them using a custom filtering script (filter_scholarships.py) that utilizes Pandas to compare user input with the dataset.
Dataset: A cleaned and structured JSON/CSV file containing global scholarship data was used.
Integration: Flask-CORS enabled cross-origin requests. Optional Gemini API integration was explored for AI summarization and explanations.

Challenges we ran into

Creating a reliable matching algorithm without access to real-time scholarship APIs.
Structuring the dataset to work efficiently with our filtering logic.
Ensuring smooth communication between React frontend and Flask backend, especially with async calls and CORS.
Designing a UI that feels intuitive but handles multiple conditions without overwhelming the user.

Accomplishments that we're proud of

Successfully built a working end-to-end scholarship matching tool in limited time.
Developed clean filtering logic using rule-based logic and Pandas.
Built a chatbot UI that feels engaging, user-friendly, and efficient.
Created a scalable backend structure that could be expanded with live data and AI features.

What we learned

How to connect a React frontend with a Python Flask backend using Axios and manage data flow between them.
Practical use of Pandas for real-time filtering of large datasets.
The importance of good UX in user data collection, especially when the data is multi-variable and sensitive.
Basics of integrating AI APIs (Gemini) to enhance the user experience through summaries or explanations.

What's next for ScholarBuddy

Integrate live scholarship data sources or partner APIs to replace static datasets.
Implement basic machine learning to improve matching precision over time.
Add multilingual support to increase accessibility.
Enable user accounts to save matched scholarships and track application progress.
Integrate Gemini or similar LLMs to generate detailed, personalized funding advice.