Analysis Prediction of Prambanan Temple Visitors with Fuzzy Time Series Chen Model and Seasonal Auto Regressive Integrated Moving Average (SARIMA) Model

A comparative analysis of visitor prediction models for Prambanan Temple reveals that the Seasonal Auto Regressive Integrated Moving Average (SARIMA) model outperforms the Fuzzy Time Series Chen Model in accuracy. The study, based on data from 2018, found that visitor numbers during holidays increased by 8% compared to the previous year, underscoring the need for precise forecasting to enhance service quality and attractiveness. By leveraging seasonal data characteristics, both models were tested, with SARIMA demonstrating lower prediction errors, thereby offering a more reliable tool for managing tourist flows and optimizing resources at this significant cultural site.

Artika, R., Setiawan, A., Setyowisnu, G. E., Uminasiah, S., & Prihantini. (2020). Analysis Prediction of Prambanan Temple Visitors with Fuzzy Time Series Chen Model and Seasonal Auto Regressive Integrated Moving Average (SARIMA) Model. Proceeding International Conference on Science and Engineering, 3, 359–363. https://doi.org/10.14421/icse.v3.528