Agriculture and accessories contribute to approximately 17% of India's GDP, still the most popular occupation amongst 70% of India's population. The agriculture sector provides different outputs used by diverse segments, including, but not limited to, use as raw materials by various industries, sources of nutrition and businesses, etc. Indian farmer still struggles to pick up the right crop for the proper biological and non-biological factors. Thus, in this case, different machine-learning techniques have been proposed for paddy growth with weather datasets to accelerate the paddy yield of crops. In this paper, we present a summarization of these different approaches: the regression model, random forest, and random tree. These techniques are a part of the paradigm, Precision Agriculture, specifically in paddy data analysis. These algorithms consider and implement external factors, like meteorological data like rainfall and temperature and others like pesticides, to give the best recommendations, which not only lead to better yields but also minimum use of resources and capital.