Rice Yield Forecasting: A Comparative Analysis of Multiple Machine Learning Algorithms

Agriculture plays a crucial role in Nigeria's economy, serving as vital source of sustenance and livelihood for numerous Nigerians. With the escalating impact climate change on crop yields, it becomes imperative to develop models that can effectively study predict rice output under varying climatic conditions. This collected yield data from Katsina state, spanning years 1970 2017, sourced Nigeria Bureau Statistics. Additionally, same period were obtained World Bank Climate Knowledge portal. Logistic Regression (LR), Artificial Neural Network (ANN), Random Forest (RF), Trees (RT), Naïve Bayes (NB) employed prediction utilizing this dataset. The findings reveal random forest trees exhibited superior classification performance prediction. developed offer promising tool predicting future facilitating proactive measures ensure food security people state.