Pemodelan GSTARX Untuk Peramalan Jumlah Wisatawan Pada Tiga Objek Wisata Di Kota Batu

Rhema, Elsa Vidya Nur (2019) Pemodelan GSTARX Untuk Peramalan Jumlah Wisatawan Pada Tiga Objek Wisata Di Kota Batu. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06111540000042-Undergraduate_Theses.pdf Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Pariwisata berkembang sangat pesat, karena itu diperlukan adanya pendekatan kuantitatif dalam menganalisis data kepariwisataan dengan melakukan peramalan jumlah wisatawan dengan metode deret berkala. Peramalan data deret berkala untuk kasus yang melibatkan banyak parameter (multivariate time series) yang tidak hanya mengandung keterkaitan dengan kejadian pada waktu sebelumnya, tetapi juga mempunyai keterkaitan dengan lokasi lain disebut dengan data space-time. Pada penelitian ini, dikembangkan pemodelan Generalized Space-Time Autoregressive with Exogenous Variables (GSTARX). GSTARX adalah model yang menggabungkan unsur dependensi waktu dan lokasi pada suatu data multivariate time series yang melibatkan variabel eksogen berupa variasi kalender serta pembobotan lokasi dengan bobot lokasi seragam dan invers jarak. Berdasarkan Root Mean Square Error (RMSE) terkecil, model terbaik yang didapat pada data adalah model GSTARX dengan estimasi parameter Ordinary Least Square (OLS) pada bobot lokasi invers jarak. Hasil peramalan yang dilakukan untuk jumlah wisatawan pada tiga objek wisata di Kota Batu menunjukkan bahwa pada bulan-bulan liburan sekolah jumlah wisatawan pada ketiga objek wisata cenderung meningkat.
=============================================================================================================================
Tourism is growing very rapidly, therefore a quantitative approach is needed in analyzing tourism data by forecasting the number of tourists with the periodic method. Periodic data forecasting for cases involving multiple parameters (multivariate time series) which does not only contain links with events in the previous time, but also has relevance to other locations is called space-time data. In this study, a Generalized Space-Time Autoregressive with Exogenous Variables (GSTARX) model was developed. GSTARX is a model that combines time and location dependency elements in a multivariate time series data involving exogenous variables in the form of calendar variations and weighting locations with uniform location and inverse distance weights. Based on the smallest Root Mean Square Error (RMSE), the best model obtained in the data is GSTARX model with Ordinary Least Square (OLS) parameter estimation with the inverse distance weighting location. The forecasting results carried out for the number of tourists in three tourist attractions in Batu City showed that in the months of school holidays the number of tourists in the three tourist attractions tended to increase.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	multivariate, space-time, GSTARX, variasi kalender
Subjects:	Q Science > QA Mathematics Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression Q Science > QA Mathematics > QA278 Cluster Analysis. Multivariate analysis. Correspondence analysis (Statistics)
Divisions:	Faculty of Mathematics and Science > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Elsa Vidya Nur Rhema
Date Deposited:	06 Aug 2026 03:41
Last Modified:	06 Aug 2026 03:41
URI:	http://repository.its.ac.id/id/eprint/65677

Actions (login required)

View Item