Comparison of Arima, Transfer Function and Var Models for Forecasting Cpi, Stock Prices, and Indonesian Exchange Rate: Accuracy vs. Explainability

Purwa, Taly; Nafngiyana, Ulin; Suhartono, Suhartono

doi:10.14710/medstat.13.1.1-12

Cited by 7 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This condition indicates that the models are suitable for short-term forecasting (two weeks at maximum) as confirmed by the percentage of RMSE that can be reduced by the ARIMA or ARIMAX and VARX model from the error measures generated from mean-based forecasting as a benchmark in Figure 6. This procedure also was conducted in previous study [15]. The RMSE reduction decreases as the forecasting horizon increases for all methods, even significantly decrease for one month forecasting and getting worse for two months forecasting horizon since it has negative values.…”

Section: Selection Of the Overall Best Modelmentioning

confidence: 82%

Assessing Forecasting Performance of Daily Mean Temperature at 1st and 2nd Perak Station, Surabaya Using ARIMA and VARIMA Model with Outlier Detection

Purwa

Ngwarati²

2022

Jambura J. Math

Self Cite

View full text Add to dashboard Cite

Air temperature is an important data for several sectors. The demand of fast, exact and accurate forecast on temperature data is getting extremely important since it is useful for planning of several important sectors. In order to forecast mean daily temperature data at 1st and 2nd Perak BMKG Station in Surabaya, this study used the univariate method, ARIMA model and multivariate method, VARIMA model with outlier detection. The best ARIMA model was selected using in-sample criteria, i.e. AIC and BIC. While for VAR model, the minimum information criterion namely AICc value was considered. The RMSE values of several forecasting horizons of out-sample data showed that the overall best model for mean daily temperature at 1st and 2nd Perak Station was the multivariate model, i.e. VARX (10,1) with four outliers incorporated in the model, indicated that it was necessary to consider the temperature from the nearest stations to improve the forecasting performance. This study recommends performing the overall best model only for short term forecasting, i.e. two weeks at maximum. By using the one week-step ahead and one day-step ahead forecasting scheme, the forecasting performance is significantly improved compared to default the k-step ahead forecasting scheme.

show abstract

Section: Selection Of the Overall Best Modelmentioning

confidence: 82%

Assessing Forecasting Performance of Daily Mean Temperature at 1st and 2nd Perak Station, Surabaya Using ARIMA and VARIMA Model with Outlier Detection

Purwa

Ngwarati²

2022

Jambura J. Math

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, the value of the Bank Indonesia benchmark interest rate (BI Rate) can be forecasted using the transfer function [7], [8]. Research related to transfer functions is in [9], which examines the accuracy of the transfer function and vector autoregressive models in currency exchange rates. The transfer function forecasts the Bank Indonesia benchmark interest rate (BI Rate) if the value of gold prices fluctuates.…”

Section: Introductionmentioning

confidence: 99%

Transfer Function and Arima Model for Forecasting Bi Rate in Indonesia

Khikmah,

Sadik,

Indahwati

2023

BAREKENG: J. Math. & App.

View full text Add to dashboard Cite

Fluctuating gold prices can have an impact on various sectors of the economy. Some of the impacts of rising and falling gold prices are inflation, currency exchange rates, and the value of the Bank Indonesia benchmark interest rate (BI Rate). The data was taken from the Indonesian Central Statistics Agency's official website (BPS) for the Bank Indonesia benchmark interest rate (BI Rate) value. Therefore, research on the value of the Bank Indonesia benchmark interest rate (BI Rate) is essential with the gold price as a control. The purpose of this study is to forecast the value of the Bank Indonesia reference interest rate (BI Rate) with a transfer function model where the input variable used is the price of gold and forecast the value of the Bank Indonesia benchmark interest rate (BI Rate) with the ARIMA model. The analysis results show that the best model for forecasting the Bank Indonesia reference interest rate (BI Rate) is a transfer function model with a value of , , , and a noise series model with the MAPE value is

show abstract

“…The transfer function includes the coefficient of moving average (MA) and autoregressive (AR) [18]. It is a time series approach that can explain the dynamic series case in the model prediction [19].…”

Section: Introductionmentioning

confidence: 99%

Comparison study of transfer function and artificial neural network for cash flow analysis at Bank Rakyat Indonesia

Faricha¹,

Ulyah

Susanti

et al. 2022

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">The cash flow analysis is essential to examine the economic flows in the financial system. In this paper, the financial dataset at Bank Rakyat Indonesia was used, it recorded the sources of cash inflow and outflow during a particular period. The univariate time series model like the autoregressive and integrated moving average is the common approach to build the prediction based on the historical dataset. However, it is not suitable to estimate the multivariate dataset and to predict the extreme cases consisting of nonlinear pairs between independent-dependent variables. In this study, the comparison of using two types of models i.e., transfer function and artificial neural network (ANN) were investigated. The transfer function model includes the coefficient of moving average (MA) and autoregressive (AR), which allows the multivariate analysis. Furthermore, the artificial neural network allows the learning paradigm to achieve optimal prediction. The financial dataset was divided into training (70%) and testing (30%) for two types of models. According to the result, the artificial neural network model provided better prediction with achieved root mean square error (RMSE) of 0.264897 and 0.2951116 for training and testing respectively.</span>

show abstract

Comparison of Arima, Transfer Function and Var Models for Forecasting Cpi, Stock Prices, and Indonesian Exchange Rate: Accuracy vs. Explainability

Cited by 7 publications

References 19 publications

Assessing Forecasting Performance of Daily Mean Temperature at 1st and 2nd Perak Station, Surabaya Using ARIMA and VARIMA Model with Outlier Detection

Assessing Forecasting Performance of Daily Mean Temperature at 1st and 2nd Perak Station, Surabaya Using ARIMA and VARIMA Model with Outlier Detection

Transfer Function and Arima Model for Forecasting Bi Rate in Indonesia

Comparison study of transfer function and artificial neural network for cash flow analysis at Bank Rakyat Indonesia

Contact Info

Product

Resources

About