title: PERBANDINGAN AKURASI PERAMALAN INDEKS HARGA KONSUMEN DENGAN MENGGUNAKAN METODE GARCH DAN ANN
creator: Mukhlisin, Zaenal
subject: 510 Matematika
description: The Consumer Price Index (CPI) is the most widely used indicator in determining   inflation rate. Therefore, it is essential to discover the value of CPI in the future to become the basis of government in making the appropriate and accurate policies.   The CPI data used in the current study was obtained from BPS-Statistics Indonesia   (BPS) from the period of January 2006 – December 2021. The pattern of CPI data   used in this study indicates the presence of heteroskedasticity. Consequently, as a   means to overcome the heteroskedasticity indication, researchers applied GARCH   and ANN methods to determine the value of CPI in the future. The GARCH method   is a method that capable of overcoming heteroskedasticity indication in time series   forecasting process whereas ANN method is an effective method for time series   forecasting process considering its high accuracy level. The research finding shows   that MAPE error calculation through ARIMA (4,2,2)~GARCH(1,1) model is 3,19% or with 96,81% accuracy, and ANN with 2 hidden layers is 1,24% or with 98,76% accuracy. Hence, the result of this study is that ANN method is the most appropriate method in forecasting Consumer Price Index (CPI)
publisher: Fakultas Matematika dan Ilmu Pengetahuan Alam
date: 2022-05-12
type: Skripsi
type: NonPeerReviewed
format: text
identifier: http://digilib.unila.ac.id/62977/4/ABSTRAK.pdf
format: text
identifier: http://digilib.unila.ac.id/62977/2/SKRIPSI%20FULL.pdf
format: text
identifier: http://digilib.unila.ac.id/62977/3/SKRIPSI%20FULL%20TANPA%20BAB%20PEMBAHASAN.pdf
identifier:   Mukhlisin, Zaenal  (2022) PERBANDINGAN AKURASI PERAMALAN INDEKS HARGA KONSUMEN DENGAN MENGGUNAKAN METODE GARCH DAN ANN.  Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Lampung.     
relation: http://digilib.unila.ac.id/62977/