Optimizing and Understanding the Traveling Tourist Problem

"Underground" Location Discovery
Itinerary

Inspiration

We aimed to create a service that allows adventurous travelers to discover "hidden gems"—high-quality yet underrated attractions. Our goal is to help travelers live like locals while promoting small businesses.

What it does

Our service highlights businesses with positive sentiments but fewer reviews in our travel itinerary. Users can select their starting point and time, and the service will automatically plan their day. There’s also an option to include popular tourist spots if desired.

How we built it

We fetched and cleaned TourPedia API data according to our "underground" and "tourist-trap" criteria using Python. With Folium, we identified clusters of high-quality locations and pinpointed popular destinations. Using the traveling tourist algorithm, we then mapped out the most optimal path based on user preferences.

Challenges we ran into

Optimizing the traveling tourist problem was challenging, often resulting in a local minimum issue. Incorrect distance calculations led to incomplete routes where not all nodes were visited, trapping us in a local minimum.

Accomplishments that we're proud of

We successfully created an interactive website that can help the average person plan their vacation while promoting small businesses. We're excited to provide a platform that brings recognition to local gems.

What we learned

We discovered that even in the most "touristy" cities, numerous "underground" businesses exist. Many highly rated establishments lack the recognition they deserve, and we're eager to change that.

What's next for Optimizing and Understanding the Traveling Tourist Problem

Currently, the dataset covers only 8 cities from the API. Our goal is to gather more data and expand to other cities, as the model works universally as long as sufficient data is available.