Optimizing the 2024 Governor Election Quick Count with Extreme Gradient Boosting (XGBoost) to Increase Voting Prediction Accuracy

Abstract

This research aims to increase the accuracy of vote predictions in the Quick Count process in the 2024 Governor Election using the XGBoost algorithm. Quick Count is a fast method for obtaining estimates of election results based on some of the data that has been calculated. The XGBoost algorithm was chosen because it has proven effective in various applications, including predictive modeling. This research analyzes the implementation of the XGBoost algorithm in modeling vote predictions for Quick Count, especially in the context of the 2024 gubernatorial election. By using various evaluation metrics such as accuracy, precision, recall, and F1-score, this research provides a comprehensive understanding of the performance of the XGBoost model. The research results show that the XGBoost algorithm achieves high accuracy, precision, recall, and F1 score, demonstrating its ability to classify sounds accurately. The practical implications of this research are significant in improving the integrity of the democratic process by providing more reliable and transparent election results. Additionally, this research paves the way for developing more sophisticated Quick Count methods by leveraging insights from previous research on machine learning techniques and data security.