Optimizing Agricultural Productivity: A Machine Learning-Based Approach for Precision Crop Recommendation

Agriculture serves as the cornerstone of India’s economy and employment landscape. However, a significant challenge faced by Indian farmers is the lack of optimal crop selection for their soil, leading to reduced productivity and economic strain. This issue has exacerbated food shortages and contributed to a distressing increase in farmer suicides. To address this, recommending suitable crops based on soil characteristics is crucial. Modern agricultural practices emphasize the need for analyzing soil nutrients, such as potassium, nitrogen, and phosphorus, to mitigate deficiencies and enhance crop growth. Moreover, diversifying crop varieties through experimentation is essential for sustainable farming. Aiming to empower farmers with informed decisions, this paper explores various predictive models, including Navies Bayes, Decision Tree, Bagging, Random Forest with the accuracy of 98% to determine the most effective approach for crop prediction based on soil attributes.