Implementation of Hotel Recommendation System with Integrated Machine Learning Models

The objective of this project is to design and develop a recommendation system involving hotels using collaborative filtering and using algorithms like General Adversarial Network (GAN) and K-Nearest Neighbor (KNN). It also aims to optimize the price of a room in a hotel based on historical data and using Random Forest Regression algorithm. The tool will provide users a platform to search for a hotel according to their preferences and based on the various reviews provided by the users across different websites. The system will use General Adversarial Network to generate synthetic ratings for users who may have not rated some hotels. This is useful to fill in the gaps where users have not interacted with certain hotels. By using KNN, the goal is to recommend hotels to users based on the preferences of similar users. KNN helps find these similar users by computing the similarity based on user ratings and then uses these similar users' ratings to recommend new hotels. A comparison between GAN and KNN is also done using various parameters like accuracy, precision. The system will use collaborative filtering to predict user preferences and show relevant results about hotels thereby making it easier for them to choose hotels. The cost of a hotel is predicted using Random Forest Regression according to different seasons.