Abstract: The purpose of this study is to improve the prediction of contraceptive uptake with the use of the stacked ensemble model. The main objectives include the identification of the relevant predictors associated with that uptake, development of ensemble designs for improving the accuracy and robustness of prediction, the implementation involved in these models, and performance evaluation. The proposed ensemble model encompasses four MLAs: Support Vector Machine, Random Forest, Decision Tree, and KNN, respectively, while Logistic Regression will be the meta learner. Due care was taken for the collection and preprocessing of data by discretization, normalization, and cleansing. Next, feature selection was done based on Information Gain and Chi-Square methods in order to focus only on the most relevant predictors. The ensemble model was implemented in Python and the performance of the model evaluated using Accuracy, Precision, Recall, and F1 score. The performance was able to give an accuracy of 0.8187, precision of 0.8223, recall of 0.8187, and F1 score of 0.8198-in effect, a balance in all the metrics. The ensemble model was much more robust and reliable compared to the single models, hence a tool in the prediction of uptake of contraceptives. Overall, the performance of the ensemble model suggests that sophisticated machine learning algorithms will significantly support healthcare providers with informed contraceptive recommendations to better the outcomes of family planning. Future research may investigate other predictors and longitudinal data further to improve model performance and generalizability across diverse healthcare domains. Keywords: Contraceptive uptake, ensemble learning, machine learning, prediction model, stacked ensemble, Support Vector Machine (SVM), Random Forest, Decision Tree, K-Nearest Neighbors (KNN), Logistic Regression, feature selection, accuracy, precision, recall, F1 score, healthcare data, family planning. Title: DEVELOPMENT OF ENSEMBLE PREDICTIVE MODELS FOR CONTRACEPTIVE UPTAKE IN WOMEN Author: Joda Shade Christiana, Prof. O.O. Obe, Prof. O.K. Boyinbode, Prof B.N. Olagbuji International Journal of Computer Science and Information Technology Research ISSN 2348-1196 (print), ISSN 2348-120X (online) Vol. 12, Issue 4, October 2024 - December 2024 Page No: 64-76 Research Publish Journals Website: www.researchpublish.com Published Date: 28-December-2024 DOI: https://doi.org/10.5281/zenodo.14564997 Paper Download Link (Source) https://www.researchpublish.com/papers/development-of-ensemble-predictive-models-for-contraceptive-uptake-in-women