FORECASTING DOMESTIC TOURIST ARRIVALS IN TEGAL REGENCY USING A HYBRID SARIMA–LONG SHORT-TERM MEMORY MODEL

SAPUTRI, ASIH (2026) FORECASTING DOMESTIC TOURIST ARRIVALS IN TEGAL REGENCY USING A HYBRID SARIMA–LONG SHORT-TERM MEMORY MODEL. Undergraduate thesis, UNIVERSITAS PEMBANGUNAN NASIONAL VETERAN JAWA TIMUR.

	Text (COVER) 21081010053_COVER.pdf Download (593kB)
	Text (BAB 1) 21081010053_BAB 1.pdf Download (187kB)
	Text (BAB 2) 21081010053_BAB 2.pdf Restricted to Registered users only until 22 July 2029. Download (396kB)
	Text (BAB 3) 21081010053_BAB 3.pdf Restricted to Registered users only until 22 July 2029. Download (583kB)
	Text (BAB 4) 21081010053_BAB 4.pdf Restricted to Registered users only until 22 July 2029. Download (749kB)
	Text (BAB 5) 21081010053_BAB 5.pdf Download (171kB)
	Text (DAFTAR PUSTAKA) 21081010053_DAFTAR PUSTAKA.pdf Restricted to Repository staff only until 22 July 2029. Download (179kB)
	Text (LAMPIRAN) 21081010053_LAMPIRAN.pdf Restricted to Repository staff only until 22 July 2029. Download (396kB)

Abstract

This study aims to analyze the performance of the Hybrid SARIMA-LSTM model in forecasting domestic tourist arrivals in Tegal Regency. The forecasting was conducted to support the development of a system capable of identifying fluctuations in tourist arrivals, thereby providing a basis for decision-making by the government and tourism industry stakeholders. The model was developed by integrating the Seasonal Autoregressive Integrated Moving Average (SARIMA) model with the Long Short-Term Memory (LSTM) model to form a hybrid forecasting approach. The research process included data collection and preprocessing, SARIMA modeling, and LSTM modeling using the residuals generated by the SARIMA model. The model was then evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) to assess its forecasting accuracy. The results showed that the Hybrid SARIMA-LSTM model was more effective in capturing data patterns consistently than the standalone SARIMA model. Furthermore, it successfully modeled linear, seasonal, and nonlinear patterns in the historical data, resulting in more stable forecasts and lower prediction errors.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	RAHAJOE, ANI DIJAH	NIDN0012057301	anidijah.if@upnjatim.ac.id
Thesis advisor	PUSPANINGRUM, EVA YULIA	NIDN0005078908	evapuspaningrum.if@upnjatim.ac.id

Subjects:

Q Science > Q Science (General)
Q Science > QA Mathematics
Q Science > QA Mathematics > QA76 Computer software
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Asih Saputri -

Date Deposited:

22 Jul 2026 07:44

Last Modified:

22 Jul 2026 07:44

URI:

https://repository.upnjatim.ac.id/id/eprint/57698