Paper Title
A STACKING ENSEMBLE APPROACH FOR MILK YIELD PREDICTION ON DAIRY CATTLE

Abstract
Abstract – Knowing expected milk yield can help dairy farmers in better decision-making and management. The objective of this study was to build and compare predictive models to forecast dailymilkyieldoveralongduration.Amachine-learningpipeline was provided and five baseline models as well as a novel stacking model were developed for the prediction of milk yield on the CowNflow dataset using 414 Holstein cattle records collected from1983to2019.Fourdifferentfeatureselectionmethods were performed to evaluate the essential features that affectmilk yield. The results showed that the overall performance of predictive models improved after proper feature selection, with an R2value increased to 0.811, and a root mean squared error (RMSE)decreasedto3.627.Thestackingmodelachievedthebest performance with an R2value of 0.85, a mean absolute error (MAE) of 2.537 and an RMSE of 3.236. This research provides benchmark information for the prediction of milk yield on the CowNflowdatasetandidentifiedusefulfactorsinlong-termmilk yield prediction. Keywords - Milk production, Machine Learning, Feature selection