Improving the Voter List Clustering Model Fixed(DPT) using the K-Means Algorithm in Girinata Village

Elections are one of the pillars of democracy that require accurate voter data to ensure transparency and fairness. The Permanent Voter List (DPT) is a crucial element in supporting the smooth running of elections, but there are often data validity problems such as duplicate data, voter location errors, or voter data that does not meet the requirements. This research focuses on the application of the K-Means algorithm to increase the accuracy and validity of the DPT at TPS 05, Girinata Village. The problem formulation in this research includes the accuracy level of the DPT, the effectiveness of the K-Means algorithm in identifying inaccuracies, as well as factors that influence the accuracy of voter data. This research aims to analyze the accuracy level of the DPT, evaluate the effectiveness of the K-Means algorithm in grouping data, and identify factors contributing to the validity of the DPT. The analysis results show that the K-Means algorithm succeeded in grouping voter data with good quality, with a Davies-Bouldin Index (DBI) value of 0.389, which indicates clearly defined clusters. The main factors that influence clustering are age, distance to TPS, and location (RT and TPS). This research shows that the K-Means algorithm can be used to detect inaccuracies in voter data, such as data that does not match the TPS location or age that does not meet the requirements as a voter. With these results, the K-Means algorithm makes a significant contribution to validating voter data, thereby supporting a more transparent and accountable election process.