COMPARATIVE ANALYSIS OF MACHINE LEARNING ALGORITHMS FOR CROP YIELD PREDICTION

Abstract

Crop yield prediction plays a critical role in agricultural planning, food security, and economic stability. Accurate forecasting enables farmers, policymakers, and agricultural stakeholders to make informed decisions regarding crop selection, resource allocation, and risk management. With the increasing availability of agricultural data and advancements in computational techniques, machine learning has emerged as an effective approach for improving prediction accuracy. This study presents a comparative analysis of multiple machine learning algorithms for predicting crop yield based on historical agricultural data. The dataset used includes key parameters such as rainfall, temperature, soil characteristics, humidity, and previous yield records. These features are selected due to their significant influence on crop productivity. Three widely used machine learning models—Linear Regression, Decision Tree, and Random Forest—are implemented and evaluated for their predictive performance. The models are trained and tested using standard preprocessing techniques, including data cleaning, normalization, and feature selection, to ensure data quality and consistency. Performance evaluation is conducted using metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R² score). The experimental results demonstrate that ensemble-based approaches, particularly Random Forest, outperform traditional models in terms of accuracy, robustness, and generalization capability. The findings highlight the importance of selecting appropriate algorithms and relevant features to enhance prediction performance. The proposed approach provides a data-driven framework that can assist farmers and agricultural planners in optimizing crop productivity and improving decision-making processes in modern agriculture.