Class Balancing for Soil Data: Predictive Modeling Approach for Crop Recommendation Using Machine Learning Algorithms

Soil data analysis is fundamental to agricultural productivity, environmental sustainability, and land management. Traditional soil analysis methods often require extensive labor and time, prompting the need for more efficient and accurate techniques. This research investigates the potential of machine learning algorithms in transforming soil data analysis. By employing advanced machine learning methods such as decision trees, support vector machines, logistic regression, random forest and XGBoost. This study aims to predict and classify crop based on various soil properties. This research paper presents a comprehensive study of soil sample analysis using various machine learning algorithms. The objective of this study is to enhance prediction accuracy through effective class balancing and feature selection methods. Several classification algorithms, including Support Vector Classifier (SVC), Logistic Regression, Decision Tree, Random Forest, and XGBoost, were employed to predict soil characteristics. The study highlights the superior performance of the XGBoost with oversampling balancing method having an accuracy of 93.82%.