Inspiration
Data is important in unlocking insights into human behavior. With so many travelers relying on reviews to plan trips, we saw an opportunity to take that feedback further—by using machine learning to cluster travel preferences. Our goal was to go beyond individual reviews and create personalized travel experiences based on broader patterns in traveler feedback.
What it does
Using K-means clustering, this analysis uses Google Reviews to group travelers based on their preferences for different types of attractions—like museums, restaurants, and beaches. By identifying these distinct traveler groups, the analysis can predict what types of activities and destinations different consumers will prefer. This helps travel companies or planners create tailored itineraries, ensuring that trips align with individual interests and making travel planning more efficient and personalized.
How we built it
We built it using r-studio. We use machine learning techniques such as k-means clustering and random forest.
Challenges we ran into
R file is not knitting at times. Coming up with the right number of k for clusters.
Accomplishments that we're proud of
Finishing this project on time and still getting sleep.
What we learned
Perserverance.
What's next for Trip Hacking with Google Reviews
We can implement these clusters to optimize the ideal travel plans pushed to consumers.
Log in or sign up for Devpost to join the conversation.