Automated Machine Learning Based Crop Recommendation System

Abstract

Agriculture plays a crucial role in supplying food for the population, as well as 
contributing significantly to the country's Gross Domestic Product (GDP) in India. 
For farmers to achieve higher yields and profitability, it is essential to select a crop 
based on soil parameters. To simplify this process, a system for crop 
recommendation based on Machine Learning models has been developed. As a 
result, farmers may find it difficult to make informed decisions when using the 
Machine Learning approach since it is both time-consuming and exhaustive. 
Automated Machine Learning is being used to simplify and speed up the process. 
A machine learning algorithm uses an automatic selection of algorithms, features, 
and hyperparameters to make predictions, which can result in more accurate 
results. This study examines various Automated Machine Learning frameworks 
and compares the accuracy scores of different crop recommendation systems. H2O 
and AutoGluon achieved the highest accuracy score of 92.0%.