Vegetables, fruits, cereals, natural textile fibres like cotton and jute, as well as many other goods, are heavily dependent on agriculture in India. Additionally, the agriculture industry is crucial to the nation's economic development. As a result, employment in India is significantly impacted by agricultural productivity. The soil in India has been used for thousands of years, which has caused nutrient and mineral depletion and fatigue, which lowers crop productivity. Additionally, the lack of contemporary applications creates a demand for precision agriculture. A number of techniques and instruments are used in precision agriculture, commonly referred to as satellite farming, to manage farms based on the observation, measurement, and reaction to crop variability both within and between fields. The recommendation of precise crops is one of the key uses of precision agriculture. It aids in boosting crop productivity and generating revenue. The purpose of this research is to review and evaluate the effectiveness of various techniques on crop recommendation systems. In this research, we analysed and fed a crop recommendation dataset from the internet to a number of machine learning algorithms. With an accuracy of roughly 99.5%, we see that the model developed using the Gaussian Naive Bayes technique exceeds all other models.