A constraint-based travel recommendation engine that generates optimized itineraries from user-defined parameters.
🏅 5th Place — 2022 FBLA State Competition
Planning travel is time-consuming — cross-referencing budget constraints, weather conditions, and local attractions manually is tedious and error-prone. AttractionFinder automates this by taking a user's budget and weather preferences and generating a ranked, optimized list of nearby attractions that fit their criteria.
The core algorithm parses and categorizes regional attraction datasets, applying constraint-based filtering to distinguish local hidden gems from well-known tourist destinations — achieving 95% classification accuracy.
| Feature | Description |
|---|---|
| 💰 Budget Filtering | Filters attractions based on user-defined budget constraints |
| 🌤️ Weather Awareness | Adjusts recommendations based on current or preferred weather parameters |
| 🗺️ Itinerary Generation | Produces ranked, optimized travel plans from combined constraints |
| 🔍 Smart Categorization | Distinguishes local gems from major tourist hubs with 95% accuracy |
| 🖥️ Cross-Platform | Runs on Windows 10/11, Linux, and macOS |
| Technology | Purpose |
|---|---|
| Python 3.5+ | Core recommendation engine (~745 lines) |
| CustomTkinter | Desktop GUI |
| Data filtering algorithms | Constraint-based itinerary optimization |
Key Engineering: Implemented advanced data filtering and parsing algorithms to categorize regional attraction datasets. The constraint engine chains budget, weather, and location parameters into a single optimized recommendation pass.
- Windows 10/11, Linux, or macOS
- Stable internet connection
- 25 MB disk space, 2 GB RAM
# 1. Download and extract the ZIP
# 2. Ensure the assets/ folder is in the same directory as the executable
# 3. Run the executable
"Attraction Finder.exe"AttractionFinder/
├── assets/ # UI assets, icons, images
├── sources/ # Python source code (~745 lines)
├── Attraction Finder.exe # Compiled executable
└── Attraction Finder Documentation.pdf # Full project documentation
Built for the 2022 FBLA State Competition, earning 5th Place out of competing student development teams statewide. Full project documentation is included in the repo.
Riyon Praveen — Computer Science Student, University of South Florida
