Intelligent Crop Recommender System for Yield Prediction Using Machine Learning Strategy

For most developed nations, agriculture is a significant economic force. The realm of contemporary agriculture is consistently growing with evolving farming techniques and agricultural innovations. Farmers face challenges in keeping pace with the evolving demands of the planet and meeting the requirements of profitable initiatives, characters, and various other stakeholders. Climate change brought on by industry emissions and soil erosion, soil's nutrient deficiency due to mineral's absence, which results in reduced crop growth, and the cultivation of the same crops repeatedly without trying out new varieties are a few of the difficulties farmers face. Without considering the lower quality or quantity, they arbitrarily infuse fertilizers. Using two separate metrics, entropy and Gini indexes, the study analyzes well-known procedures with K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) classifier practices. Moreover, the precision under the agriculture paradigm, particularly “crop recommender systems,” includes these methods. Based on the outcomes, the random forest strategy outperforms the other approaches to model accuracy and reliability. © The Institution of Engineers (India) 2024.