Application of Machine Learning for Business Licensing Data Analytics at the Investment and One-Stop Integrated Service Office of South Tapanuli Regency

Abstract

The rapid growth of digital government initiatives has encouraged public institutions to utilize data-driven technologies to improve service quality and operational efficiency. One of the government agencies responsible for providing business licensing services is the Investment and One-Stop Integrated Service Office (DPMPTSP) of South Tapanuli Regency. The increasing volume of business licensing applications generates a large amount of data that can be analyzed to support decision-making and enhance service performance. However, conventional data processing methods often fail to extract valuable insights from historical licensing records. Therefore, this study applies Machine Learning techniques to analyze business licensing data and identify patterns that can support more effective and efficient public service delivery. The research methodology consists of data collection, data preprocessing, feature selection, model development, and performance evaluation. Several Machine Learning algorithms, including Naïve Bayes, Decision Tree, Support Vector Machine (SVM), and Random Forest, were implemented and compared using Accuracy, Precision, Recall, and F1-Score metrics. The dataset used in this study contains business licensing records obtained from DPMPTSP South Tapanuli Regency. The experimental results show that the Random Forest algorithm achieved the best performance with an accuracy of 93.80%, precision of 92.70%, recall of 92.10%, and F1-score of 92.40%. Furthermore, the analysis revealed that the trade sector recorded the highest number of licensing applications compared to other business sectors. The findings demonstrate that Machine Learning can effectively support business licensing data analytics and provide valuable insights for improving public service performance. The generated information can assist DPMPTSP in identifying licensing trends, optimizing resource allocation, and supporting data-driven decision-making. Consequently, the implementation of Machine Learning has significant potential to enhance the efficiency, effectiveness, and quality of business licensing services while supporting digital transformation initiatives in public administration.