A Machine Learning-Based Comparative Approach to Predict the Crop Yield Using Supervised Learning With Regression Models
Bharati Panigrahi, Krishna Chaitanya Rao Kathala, M. Sujatha
Abstract
Agriculture is essential for the existence of all human beings. It is not only a need, but it also contributes to national growth. Agriculture is the only industry that benefits both itself and the rest of the country. It not only offers food and raw materials to a substantial section of the people but also work prospects. Agriculture is the principal source of income for the majority of people in India. It has been in the country for thousands of years, and modern technology and equipment have substituted ancient farming practices. With the advancement of technology in every industry, it has become increasingly vital to incorporate technology into agriculture. Machine learning facilitates the study of large volumes of data and may deliver faster and more precise results, which can aid in the identification of lucrative possibilities and risky threats. The major goal of this research project is to develop a Machine Learning (ML) model to predict farm production. To estimate crop yields, the data was collected and trained using supervised machine learning with six distinct regression models. With a Mean absolute error (MAE) of 468.16 and a Cross-Validation score of 0.6087, Random Forest Regressor outperformed the other models.