Peramalan Inflow Dan Outflow Antar Wilayah Di Pulau Jawa Menggunakan Metode Generalized Space-Time Autoregressive With Exogenous Variable (GSTARX)

Widiartarifa, Devind Rayhananda (2025) Peramalan Inflow Dan Outflow Antar Wilayah Di Pulau Jawa Menggunakan Metode Generalized Space-Time Autoregressive With Exogenous Variable (GSTARX). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003211054-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (16MB) | Request a copy

Abstract

Uang kartal masih memiliki peranan penting dalam sistem pembayaran di Indonesia, terutama di momen tertentu seperti hari raya dan liburan tahun baru, yang memengaruhi kebutuhan inflow dan outflow uang di Bank Indonesia. Arus inflow dan outflow uang kartal di Indonesia memiliki pola yang dipengaruhi oleh faktor temporal dan spasial. Dalam konteks Pulau Jawa, tiga provinsi utama, yakni Jawa Barat, Jawa Tengah, dan Jawa Timur, memegang peran penting dalam perekonomian nasional, dengan aktivitas inflow dan outflow yang saling berkaitan. Kelebihan atau kekurangan uang tunai di suatu wilayah dapat menyebabkan ketidakseimbangan sistem keuangan, sehingga peramalan yang akurat menjadi kebutuhan strategis. Penelitian ini bertujuan untuk menganalisis karakteristik arus inflow dan outflow uang kartal di tiga provinsi utama Pulau Jawa dan membangun model Generalized Space-Time Autoregressive with Exogenous Variable (GSTARX) yang mampu menangkap hubungan spasial dan temporal dalam distribusi uang kartal sehingga dapat memperoleh hasil peramalan uang kartal di masa depan. Hasil analisis menunjukkan pola fluktuasi dan musim yang serupa di ketiga provinsi, dengan lonjakan inflow dan outflow yang berkaitan erat dengan momen Idul Fitri. Korelasi linier positif yang signifikan juga ditemukan antarprovinsi yang mengindikasikan adanya efek dependensi antar lokasi. Pemodelan dimulai dengan melakukan pemodelan dengan regresi time series untuk data inflow dan outflow di masing-masing provinsi untuk menangkap tren, pola musiman, dan variasi kalender. Dari residual regresi tersebut akan dimodelkan dengan fungsi transfer dengan inflasi sebagai variabel input. Setelah itu, model GSTARX dibangun dalam dua skenario, skenario 1 adalah memodelkan residual regresi sedangkan skenario 2 adalah memodelkan residual fungsi transfer. Model pada skenario 2 tidak layak digunakan karena pemodelan dengan fungsi transfer dinilai tidak akurat dan efisien. Model GSTARX terbaik diperoleh dari restricted model berbobot seragam untuk inflow, dan full model berbobot biner untuk outflow. Peramalan menunjukkan lonjakan inflow pada April 2025 dan peningkatan outflow pada Maret 2025, mencerminkan karakteristik historis yang konsisten. Model ini dapat digunakan sebagai dasar strategis dalam manajemen distribusi uang kartal di Indonesia.
========================================================================================================================
Cash still plays an important role in the payment system in Indonesia, especially during certain moments such as holidays and New Year holidays, which affect the inflow and outflow needs of money at Bank Indonesia. The inflow and outflow of currency in Indonesia has a pattern that is influenced by temporal and spatial factors. In the context of Java, the three main provinces of West Java, Central Java and East Java play an important role in the national economy, with interrelated inflow and outflow activities. An excess or shortage of cash in a region can lead to financial system imbalances, making accurate forecasting a strategic necessity. This study aims to analyze the characteristics of cash inflow and outflow in the three main provinces of Java Island and build a Generalized Space-Time Autoregressive with Exogenous Variable (GSTARX) model that is able to capture spatial and temporal relationships in the distribution of cash so as to obtain future cash forecasting results. The results of the analysis show similar patterns of fluctuation and seasonality across the three provinces, with spikes in inflows and outflows closely linked to the Eid al-Fitr moment. A significant positive linear correlation was also found between provinces which indicates dependency each location. Modeling begins by performing time series regression modeling for inflow and outflow data in each province to capture trends, seasonal patterns, and calendar variations. The regression residuals will be modeled with a transfer function with inflation as the input variable. After that, the GSTARX model is built in two scenarios, scenario 1 is modeling the regression residuals while scenario 2 is modeling the transfer function residuals. The model in scenario 2 is not feasible because modeling with the transfer function is not accurate and efficient. The best GSTARX model is obtained from the uniformly weighted restricted model for inflow, and the binary weighted full model for outflow. Forecasting shows a spike in inflow in April 2025 and an increase in outflow in March 2025, reflecting consistent historical characteristics. This model can be used as a strategic basis in the management of currency distribution in Indonesia.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	GSTARX, inflow, outflow, uang kartal, variasi kalender, calendar variation, cash, GSTARX, inflow, outflow
Subjects:	Q Science Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Devind Rayhananda Widiartarifa
Date Deposited:	23 Jul 2025 01:56
Last Modified:	23 Jul 2025 01:56
URI:	http://repository.its.ac.id/id/eprint/120642

Actions (login required)

View Item