joshuarwanda/travel-destination-recommendation-sys

A recommendation system that gives users suggestions that best match their travel preferences in and around African countries. # Africura Travel Destination Recommendation System A recommendation system that gives users suggestions that best match their travel preferences in and around African countries. #### Authors * Dennis Mwanzia * Pamela Awino * Joshua Rwanda * Nelson Kemboi * Pauline Wambui * Kane Muendo * Ian Macharia ## Introduction Tourists visiting Africa often struggle to find suitable travel destinations that align with their preferences, making it challenging to plan a satisfying trip within their budget and time constraints. Our main aim as AfricuraAI is to develop a machine learning model i.e. recommendation system that provides personalized recommendations for the best tourist destinations in Africa. By considering customer reviews, budget constraints, specific locations, available amenities, and residence type, the model aims to suggest the ideal tourist destination that aligns with the user's preferences. ## Objective The goal is to build a machine learning model that can accurately predict hotel ratings based on customer reviews, budget constraints, specific locations, and the type of residence. The model will help users make informed decisions when selecting hotels by considering their preferences and constraints. ## Project Overview This project followed the CRISP-DM process. The CRISP-DM process is a data mining process model that describes commonly used approaches that data mining experts use to tackle problems. The CRISP-DM process is divided into six phases; Business Understanding, Data Understanding, Data Preparation, Modelling, Evaluation, and Deployment. The following is a brief description of each phase: - **Business Understanding**: Exploring the business reasons for our data mining effort and what the company hopes to gain from the project. - **Data Understanding**: The datasets we utilized comprised of json files scraped from tripadvisor. - **Data Preparation**: It mainly involved; selecting the data to discover the columns to be used, c …