Comprehensive Geospatial and Statistical Analysis of Restaurant Distribution Using K-means Clustering in Machine Learning Technology

Geographical distribution and characteristics of restaurants are important for players in the food industry as decisions are made based on data today. This study provides a geospatial and statistical analysis of restaurant distribution using the K-means clustering approach. Using an alternative data source, this paper aims to identify regularities and acquire information about the places where each restaurant is located concerning latitude, longitudes, prices charged, and types of cuisines This research first explored and visualized the geographical coordinates of restaurants to show how they are distributed in various places. In clustering restaurants based on their locations, this paper uses K-means to facilitate the identification of aggregate areas with many restaurants as well as their possible hot points. Additionally, this research does an in-depth review of the attributes of restaurants in the specific clusters such as average scores, popular types of food, and average price tags which can help one pinpoint locations with the most pleasant or cheapest dining options. The technique helps to indicate areas with many dining places as well as disclose important tendencies about their attribute or types in different regions. According to this research results, there is significant clustering in cities with different types of restaurants and a wide selection of meals offered. It can give restaurant owners, town developers, and marketing agents a chance to make better decisions about the most convenient places for new eating houses to maximize income. Through this research work, can able to see the method used is really good for geographical data because it could be used again in future studies.