Systematic Literature Review: The Use of the K-Nearest Neighbor Algorithm in Data Classification for Government Policy Optimization

Abstract

Along with the rapid advancement of technology and the progress of the digital era, the volume of data across various sectors has significantly increased, making it necessary to process this data to support policy optimization. Data processing is essential for simplifying complex data by grouping it according to specific characteristics. K-Nearest Neighbor (KNN) is a widely used classification algorithm in data mining implementation, applying the principle of class determination based on the proximity between data points, calculated using the Euclidean distance metric. In the governmental sector, this algorithm has been utilized to improve the efficiency of public policies and data-driven decision support systems. This study employs a Systematic Literature Review (SLR) to examine the use of the K-Nearest Neighbor algorithm in previous research for classifying government-related data as a foundation for formulating more effective and efficient policies. The information is gathered by collecting references from relevant journals and studies to provide a detailed understanding of the effectiveness of data processing as a means for optimizing government policies and offering well-targeted decision-making recommendations.