Application of XGBoost Regression in Maize Yield Prediction

Artificial Intelligence (AI) is the human-like intelligence imbued in machines so that they can perform tasks normally require human intelligence. Machine learning an AI technique which carries on concepts of predictive analytics with one important distinction: system make assumptions, test hypotheses, and learn independently. XGBoost, Extreme gradient boosting, a popular machine-learning library for regression tasks. It implements gradient-boosting decision tree algorithm, combines several feeble trees to produce robust model. In Boosted Trees, boosting process transforming poor learners into strong learners. ensemble method; weak learner classifier low correlation classification, whereas has high correlation. Maize staple food Kenya having it sufficient amounts country assures farmers' security economic stability. Crop yield measures seeds or grains produced by particular plot land. Typically, expressed kilograms per hectare, bushels acre, sacks acre. This study predicted maize Uasin Gishu, county Kenya, using XGBOOST algorithm machine learning. The model used mixed-methods research design, survey employed well-structured questionnaires comprising quantitative qualitative variables, directly administered selected representative farmers from 30 clustered wards. questionnaire comprised variables related production 900 randomly distributed across was fitted, could predict identify top features affect yield. evaluated metrics Root Mean Squared Error (RMSE), (MSE), Absolute Percentage (MAPE) (MAE), values were 0.4563, 0.2082, 25.2700 0.3532, respectively. recommended prediction.