Analisis Prediksi Kunjungan Bandara Adi Soemarmo Menggunakan Metode Time Series Berbasis Neural Network

Abstract

The increasing number of visitors at the airport requires effective operational planning to maintain service quality and efficient use of resources.. therefore, a forecasting method is needed that can accurately estimate the number of visitors in the coming period. This study aims to analyze and predict the number of visitors at Adi Soemarmo Airport using a Neural Network-based Time Series method. The data used in this study consist of historical data on airport visitor numbers collected periodically over a spesific time range. The research process includes data collection, data preprocessing splitting the data into training and testing sets, building the Neural Network model, and evaluating the prediction results. The Neural Network method was chosen because it has the ability to recognize patterns and nonlinear relationships present in time series data. Model performance was evaluated using error metrics such as Mean Square Error (MAE) and Root Mean Square Error (RMSE). The results of the study show that Neural Network model is capable of predicting the number of visitors with a high degree of accuracy and can track pattens of change in historical data. Thus, the proposed model can be used as a tool to support decision-making related to operational planning, facility management, and service improvement at Adi Soemarmo Airport. This study also shows that a time series approach based on Neural Network has good potential for predicting the number of visitors in the air transportation sector.