Smart Travel Planner using Hybrid Model

Abstract

Everybody goes on a vacation to take a break from their busy life but planning for these vacations consumes a lot of time. One of the main reasons for this is the lack of platforms that provide personalized information for vacation planning. Users must individually search for good-reviewed restaurants and hotels and plan an appropriate path to visit top tourist places according to their budget. In this project, a user's distinct preferences will be considered to guide them in recommending the route according to their interests. This study has used a hybrid model as the features planned to include are quite complex. The model built is trained on the basis of features that are derived from the collected data. As a result, the model emerged and can successfully be used to create numerous suggestions for consumers. For this Hybrid model, URLs of different tourist places are gathered from websites like TripAdvisor, and Holidify to gather information about the Point of interest using Web scraping. Here, Gaussian Mixture Model (GMM) algorithm and K-Means algorithm are applied to group the nearby attractions and hotels to understand these algorithms better.