Crop Recommendation System using Antlion Optimization and Decision Tree Algorithm
J. Avanija, Keerthi Ambati, Likitheswari Naraganti, Sai Sahith Derangula, Tanujasree Nashina
Abstract
Agriculture in India is a cornerstone of employment and economic growth, contributing significantly to the nation’s GDP. However, conventional farming practices often lead to suboptimal crop yields and financial losses due to inadequate knowledge of crop selection based on soil types and climate variability. To address this challenge, an advanced crop recommendation system is developed, integrating Ant Lion Optimization and Decision Trees (ALO-DT) to suggest optimal crop types based on ecological factors. The proposed model, trained on a Kaggle dataset, combines global optimization with decision-making precision to automatically recommend crops suited to diverse agricultural conditions. By synergizing optimization techniques with data-driven precision, the system provides tailored recommendations for varying ecological contexts, empowering farmers to make informed decisions. These recommendations not only enhance agricultural performance but also support sustainable farming practices, fostering food security and economic resilience. The proposed crop recommendation system serves as a valuable tool in agricultural decision-making, offering guidance to farmers and contributing to the advancement of sustainable agribusiness practices in india.