Recommending Geographical Proximity for Geo locational Data using Machine Learning Techniques

Abstract

The traditional approaches for investigating human mobility behaviours in big cities usually include time consuming and costly observations and questionnaires. Since then, Recommendation System (RS) has gained popularity for modeling human movements in different research contexts. Analyzing geo locational data offers valuable insights into regional human behaviour and preferences. Geographical analysis of geo located data provides useful information about regional human behaviour and choice tendencies. Nowadays, it is very important to find a convenient location that would meet all the requirements of a person at an affordable price. This project leverages data visualization and clustering techniques to identify such places within a given radius, considering parameters like cafes, gyms, parks, hospitals, bus stops, Movie theatres, and hotels. Within a given radius, places characterized by parameters such as cafes, gyms, parks, hospitals, bus stops, movie theatres, and hotels are identified through the utilization of data visualization and clustering techniques in this project. Geo locational data, acquired from the Here Geocoding and Search API v7, undergoes K Means Clustering for grouping. This clustering is applied to the geo locational data, allowing the categorization of accommodation based on user preferences for amenities. Intelligent user suggestions are generated by the Machine Learning model, which analyses both geo locational data and user preferences. The overarching objective is the classification of locations into categories of rich, average, and low amenities, with the results presented on a map for user friendly comprehension and decision making.