VTechWorks staff will be away for the winter holidays starting Tuesday, December 24, 2024, through Wednesday, January 1, 2025, and will not be replying to requests during this time. Thank you for your patience, and happy holidays!
 

CarCool: The fun way of sharing rides

Abstract

CarCool redefines carpooling by connecting users with compatible companions through its innovative 'Vibe Score' algorithm. Users can update their interests in the profile section across categories like Lifestyle, Entertainment, Outdoor Activities, and Sports. These interests are converted into a normalized vector in the backend and stored in the database. When searching for rides, the 'Vibe Score' is calculated and displayed, allowing users to sort rides in descending order based on 'Vibe Score,' alongside other sorting options, ensuring personalized and enjoyable travel experiences.

Description

CarCool revolutionizes carpooling by prioritizing social compatibility and personal interests. In the profile section, users have the flexibility to update their interests across various categories such as Lifestyle, Entertainment, Outdoor Activities, and Sports etc. These interests are then converted into a normalized vector in the backend and stored in the database, enabling the system to tailor ride recommendations based on users' preferences. When users search for rides, CarCool calculates the 'Vibe Score' for each potential match, considering the compatibility of interests between users. The 'Vibe Score' is prominently displayed, giving users insight into the likelihood of an enjoyable ride. Additionally, CarCool provides sorting options, including sorting rides in descending order based on 'Vibe Score,' allowing users to prioritize matches that align closely with their interests and preferences. Behind the scenes, CarCool utilizes Python FAST API and MongoDB, leveraging geospatial indexing for efficient location-based searches and storing user data, including interest vectors. The machine learning cosine similarity model computes the 'Vibe Score' by comparing the interest vectors of users, ensuring accurate and personalized match recommendations. On the frontend, CarCool offers a user-friendly interface developed with React.js, enhanced with Google Maps functionalities for route visualization and location autocomplete. The search feature allows users to specify their origin, destination, and date preferences, facilitating tailored ride recommendations. Furthermore, CarCool prioritizes user engagement and satisfaction by providing a seamless login experience through Firebase authentication. By incorporating users' interests into the matching process, CarCool transforms carpooling into an opportunity for meaningful connections and enjoyable travel experiences.

Keywords

Citation