Amovi

AI-powered platform that automatically discovers, filters, and centralizes student discounts to make saving money faster, simpler, and more accessible.

Comment

Inspiration

Students often miss relevant discounts because offers are scattered across multiple platforms such as retailer websites, newsletters, social media, and in-store promotions. This fragmentation makes it time-consuming and inefficient to find meaningful savings.

We built Amovi to solve this problem by centralizing discount discovery into a single platform and reducing the manual effort required to find student-specific deals.

What it does

Amovi is a web platform that automatically discovers, aggregates, and organizes discounts relevant to students.

It allows users to:

  • Access curated discounts across categories such as food, transport, software, and lifestyle
  • View consolidated offers in a single interface
  • Avoid manual searching across multiple sources
  • Quickly identify relevant and high-value savings opportunities

The system prioritizes relevance and usability over raw volume of offers.

How we built it

Amovi is a full-stack application built with modern web technologies.

Frontend:

  • React
  • TypeScript
  • Vite
  • Tailwind CSS

Backend and data layer:

  • Supabase for authentication and database management

Data and visualization:

  • Recharts for structured analytics and data representation

Core logic:

  • Automated collection of discount-related information from multiple sources
  • Categorization of deals into student-relevant groups
  • Filtering of irrelevant or expired offers
  • Ranking of discounts based on relevance and value

Challenges we ran into

  • Extracting useful information from noisy and unstructured online discount data
  • Filtering irrelevant or low-quality offers
  • Structuring heterogeneous data into a consistent format
  • Ensuring the system remains focused on student relevance rather than generic deals
  • Designing a simple and intuitive interface on top of complex data processing

Accomplishments that we're proud of

  • Built an automated pipeline that consolidates fragmented discount information
  • Designed a structured and scalable system for deal discovery
  • Created a clean and accessible user interface
  • Successfully combined data processing with a usable product experience

What we learned

  • The importance of prioritizing data relevance over volume
  • Techniques for handling noisy and inconsistent real-world data
  • How to design full-stack systems around automated data workflows
  • The trade-offs between automation and accuracy in recommendation systems

What's next for Amovi

  • Expanding real-time discount discovery across more platforms
  • Adding personalization based on user behavior and preferences
  • Introducing location-based discount recommendations
  • Developing a browser extension for real-time savings detection
  • Building a mobile application with notifications for time-sensitive deals

video link:

https://drive.google.com/file/d/1x_svHE48BAshqlkTUKQVlzbOHxGnYAdb/view?usp=sharing

Built With

Share this project:

Updates