An Acquisition Based Optimised Crop Recommendation System with Machine Learning Algorithm

The agricultural sector makes a significant economic impact in India. It contributes 19.9% to the national GDP. The prosperity of the country's economy greatly affects the country's progress and the quality of life for Indian citizens. The vast majority of farms still use antiquated methods rather than adopting a data-driven strategy to increase output and earnings. It is considered a cornerstone of India's financial structure. Since achieving independence, increasing output through the implementation of cutting-edge technologies has been a top priority. Such cutting-edge technology is the application of machine learning algorithms to forecast agricultural outcomes such as harvest size, fertilizer requirements, and the effectiveness of specific farming implements. In this research, a model was built using an optimization and an ensemble of methods to improve the precision and consistency of prediction. Classifiers based on Support Vector Machines (SVM), K Nearest Neighbors (KNN), Decision Trees (DT), and Logistic Regression (LR) were competed against those based on voting and stacking in the ensemble technique. With an accuracy of 99.32%, the Moth Flame Optimization (MFO) algorithm was utilized to recommend the best crop to be harvested.