Siniwi, Lutfiah Maharani (2024) Peramalan Kunjungan Wisatawan Menggunakan Metode Markov-Switching ARX Berdasarkan Data Google Trends dan Topik Twitter (Studi Kasus: Kunjungan Wisatawan Domestik Provinsi Bali). Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 6003212003-Master_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
6003212003-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (7MB) | Request a copy |
Abstract
Peramalan memiliki peran krusial dalam membantu merencanakan kegiatan dan strategi bisnis yang tepat pada industri pariwisata. Kualitas peramalan dapat ditingkatkan dengan adanya data yang beragam dan mudah diakses melalui website serta media sosial. Markov-Switching Autoregressive Model with Exogenous Input (MSARX) adalah model regresi yang menggabungkan model Markov-Switching Autoregressive (MSAR) dengan variabel input yang dapat mempengaruhi deret output. Model ini memungkinkan adanya perubahan struktur secara dinamis dalam hubungan antara deret input dan output. Penelitian ini dilakukan untuk peramalan jumlah kunjungan wisatawan domestik ke Bali menggunakan metode MSARX berdasarkan indeks Google Trends dan topik Twitter dari bulan Januari 2013 hingga Desember 2022. Indeks Google Trends dianalisis berdasarkan kata kunci yang berkaitan dengan aspek pariwisata seperti kuliner, transportasi, rekreasi, akomodasi, dan perbelanjaan, yang sering dicari oleh calon wisatawan. Sementara itu, data Twitter dipilih berdasarkan kata kunci “liburan Bali” menghasilkan lima topik utama menggunakan metode Latent Dirichlet Allocation (LDA). Pemilihan model peramalan terbaik dalam penelitian ini didasarkan pada nilai Mean Absolute Percentage Error (MAPE) dan Root Mean Square Error (RMSE) terkecil. Model MSARX memiliki nilai MAPE serta RMSE lebih kecil dari model MSAR. Temuan ini menggarisbawahi pentingnya integrasi data media sosial dan tren pencarian dalam meramalkan permintaan pariwisata, yang membantu dalam pengambilan keputusan dan perencanaan strategi yang lebih efektif dalam sektor pariwisata.
=============================================================================================================================
Forecasting plays a crucial role in helping to plan appropriate business activities and strategies in the tourism industry. The quality of forecasting can be improved with diverse data that is easily accessible through websites and social media. Switching-Markov Autoregressive Model with Exogenous Input (SMARX) is a regression model that combines the Switching-Markov Autoregressive (SMAR) model with exogenous variables that can affect the input variable. This model allows for dynamic structural changes in the relationship between input and output series. This study was conducted to forecast the number of domestic tourist visits to Bali using the SMARX method based on the Google Trends index and Twitter topics from January 2013 to December 2022. The Google Trends index is analyzed based on keywords related to tourism aspects such as culinary, transportation, recreation, accommodation, and shopping, which are often searched by potential tourists. Meanwhile, Twitter data was selected based on the keyword "Bali vacation" resulting in five main topics using the Latent Dirichlet Allocation (LDA) method. The selection of the best forecasting model in this study is based on the smallest Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) values. The SMARX model has a smaller MAPE and RMSE value than the SMAR model. The findings underscore the importance of integrating social media data and search trends in forecasting tourism demand, which helps in more effective decision-making and strategy planning in the tourism sector.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Autoregressive, Google Trends, Markov-Switching, MSARX, Pariwisata, Twitter, Switching-Markov, SMARX, Tourism |
| Subjects: | Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis |
| Depositing User: | Lutfiah Maharani Siniwi |
| Date Deposited: | 12 Feb 2024 19:36 |
| Last Modified: | 12 Feb 2024 19:36 |
| URI: | http://repository.its.ac.id/id/eprint/106928 |
Actions (login required)
 |
View Item |