Optimizing Machine Learning Algorithms through Hyper-parameter Tuning for Accurate Rice Yield Forecasting in North-East, Nigeria

Accurate prediction of rice yield is crucial for strengthening food security and improving agricultural decisionmaking in North-East Nigeria, where production systems are constrained by fluctuating input use and environmental variability. This study applies four machine learning algorithms: Random Forest (RF), Extreme Gradient Boosting (XGB), Support Vector Regression (SVR), and K-Nearest Neighbours (KNN)to model rice yield using five primary farm inputs: Labour (B), Fertilizer (F), Herbicides (H), Seeds (S), and land (L)area. All models were optimized through hyper-parameter tuning to ensure reliable performance. The results show that SVM and XGB produced the strongest predictive accuracy, with RF achieving an RMSE of 14.6451 and MAD of 12.5955, while XGB achieved RMSE of 14.7739 and MAE of 12.5341. In contrast, RF and KNN recorded higher error values, indicating weaker predictive capability. To determine whether SVM and XGB differ statistically, a Wilcoxon signed-rank test was performed, yielding a non-significant p-value of 0.6756. This confirms that both ensemble model and SVM perform equivalently despite slight numerical differences. Overall, the findings demonstrate the robustness of ensemble learning techniques for rice yield prediction and provide a methodological foundation for developing datadriven agricultural decision support tools in resource-constrained environments... KEYWORDS :Rice yield prediction, Machine learning, Hyper-parameter optimisation, Random Forest, North-East Nigeria.