Land use and Land cover (LLC) classification is essential when considering the social, economic, environmental, and technological factors for planning and development of an area. It is commonly used to investigate the spatial pattern of LLC change in a particular region as well as to simulate LLC change and its influence on development. The objective of this research is to classify LLC from LISS-III satellite data using a Support Vector Machine, Random Forest Classifier, and Maximum Likelihood Classifier. Total accuracy scores are utilized using 77 random known points from Google Earth to assess the effectiveness of the classifier algorithms in LLC classification. SVM classifier obtained an overall accuracy score of 77.9%, whereas MLC produced a 77.6% overall accuracy, and RFC obtained a 71.4% overall accuracy. The result of the study shows that the SVM classifier outperforms the remaining machine learning classifiers in the LLC classification of LISS-III satellite data with a spatial resolution of 23.5 m in Prayagraj City, India.