https://doi.org/10.30598/barekengvol16iss4pp1487-1496 December 2022 Volume 16 Issue 4 Page 1487–1496 P-ISSN: 1978-7227 E-ISSN: 2615-3017 BAREKENG: Journal of Mathematics and Its Application 1487 https://ojs3.unpatti.ac.id/index.php/barekeng/ barekeng.math@yahoo.com COMPARISON IN PREDICTING THE SHORT-TERM USING THE SARIMA, DSARIMA, AND TSARIMA METHODS Muhammad Giovani 1* , Indira Anggriani 2 , Syalam Ali Wira Dinata Simatupang 3 1,2 Mathematics Study Program, Department of Mathematics and Information Technology, Kalimantan Institute of Technology 3 Statistics Study Program, Department of Mathematics and Information Technology, Kalimantan Institute of Technology Jl. Soekarno Hatta No.KM 15, Karang Joang, Balikpapan City, East Kalimantan 76127, Indonesia Corresponding author’s e-mail: ¹* giovani.smat@gmail.com Abstract. The flow of data and information grows quickly and rapidly in various sizes and means, called big data. In dealing with future changes, a mature data processing analysis and design are needed so that the prediction framework produces good results. One of the big data processing efforts is realized in the prediction or forecasting method, which is used to predict future values or trends as a reference for past conditions. One example of Big Data in Balikpapan City is the temperature within 2 meters obtained from the NASA satellite published on the power.larc.nasa.gov website. One of the methods used in this study is the ARIMA method, and development is carried out according to the data used. Based on the data to be used, namely temperature data within 2 meters in Balikpapan City, data processing is developed to pay attention to three seasonal patterns, or the Triple Seasonal ARIMA model. In this research, we can be seen how to build the Triple Seasonal ARIMA model, the Seasonal ARIMA model, and Double Seasonal ARIMA, and it can be seen the comparison of the prediction accuracy results of the three models. The results obtained in this study obtained a comparison of methods in making predictions with a specified period; the results obtained from the Seasonal ARIMA model showed that it was very good at predicting a period of 2 weeks, Double Seasonal ARIMA for a period of 1 month, Double Seasonal ARIMA for a period of 3 months, and Triple Seasonal ARIMA for a period of 6 months. Keywords: ARIMA, big data, forecasting, seasonal. rticle info: Submitted: 24 th August 2022 Accepted: 20 th November 2022 How to cite this article: M. Giovani, I. Anggriani and S. A. W. D. Simatupang, “COMPARISON IN PREDICTING THE SHORT-TERM USING THE SARIMA, DSARIMA AND TSARIMA METHODS”, BAREKENG: J. Math. & App., vol. 16, iss. 4, pp. 1487-1496, Dec., 2022. This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Copyright © 2022 Author(s)