Published Paper Details:

India is primarily an agricultural nation, and the country's economy and people's standard of living are significantly influenced by agriculture. The majority of Indian farmers have the same issue of selecting crops that aren't optimal for the climate of their area. They will thus experience a notable decline in their total output. Crops are recommended based on soil, weather, humidity, rainfall, and other geographical factors in order to handle this problem. These factors all have a major influence on crop quantity and quality. Our research's objective is to examine each of these factors, match them to the requirements unique to each crop, and offer farmers the most advantageous option. Crop selection errors are decreased as a result, and output is increased. We will use an ensemble model with a majority voting technique to achieve our goal. This model will use a combination of Decision Tree, Logistic Regression, Naive Bayes, CNN, Random Forest (RF), and Extreme Gradient (XG) Boosts learners to recommend a crop for the site-specific parameters quickly and accurately.