Search

Investment in commodities has become an alternative investment that is increasingly in demand by the public in the last fifteen years. In commodity investment, there are two things that investors consider, namely return and risk. One way to calculate risk is to use Value at Risk (VaR) and Expected Shortfall (ES). The main reason of this research is to determine the value of Value at Risk (VaR) and Expected Shortfall (ES) of selected agriculture commodities which are Wheat, Cocoa and Cotton using the time series model approach. The data used in this research is the daily closing price of selected commodities from January 3, 2017 to December 31, 2020. In the time series modeling process, the models used for predicting commodities price movements are Autoregressive Integrated Moving Average (ARIMA) for the mean model, and Generalized Autoregressive Conditional Heteroscedasticity (GARCH) for the volatility model. The values of mean and variance acquired from the model are then used to calculate the Value at Risk (VaR) and Expected Shortfall (ES) of each selected commodity. Based on the analysis, obtained that from the selected commodities, the estimated risk for selected commodities varies, where based on Value at Risk, Cotton has the lowest risk with a Value at Risk of 0.02189155, and Cocoa has the highest risk with a Value at Risk 0.02435271. However, Expected Shortfall gives a different conclusion, where Cocoa has the lowest risk with an Expected Shortfall value of 0.02435271 and Cotton has the highest risk with an Expected Shortfall value of 0.03114681. [ABSTRACT FROM AUTHOR]

Artificial Neural network are commonly used for time series forecasting, especially in financial forecasting, and when external information is useful. The aim of this study is to forecast direct economic losses of Earthquake in Indonesia using NNAR and ARIMA models and selects a model that produces a forecast with a minimum root mean square error (RMSE). The accurate prediction of the direct economic losses of earthquake is critical for allowing policy makers to take a decision to anticipate losses in the future. For the purpose of forecasting accurately, an additional method is used, namely GARCH method for resolving the white noise problem in residual, such as heteroscedasticity, autocorrelation and normality. In this paper, two interpolations are applied to expand the original small sample with virtual points. The data of direct economics losses in Indonesia during the period from 1989 to 2021 were collected from EM-DAT (The International Disaster Database). The data partitioned into training and validation periods, such that the last 5 years are the validation period. The software used for ARIMA-GARCH is EViews 10 and NNAR accomplished by forecast package in R software. Based on the analysis, obtained that the result of this study is the neural network autoregression in the training period has an RMSE of 2.412, compared to ARIMA-GARCH 9,197. The neural network autoregression is significantly worse in the validation period. Its RMSE is 24,66 versus ARIMA-GARCH 8,4. According to the RMSE value, we can notice that the ARIMA-GARCH method outperform the NNAR (4,1,20) [4] model for validation period and to forecast the direct economic losses of Earthquake in Indonesia. [ABSTRACT FROM AUTHOR]

The forecasting of ferry ticket sales aims to prepare in case of a surge in passengers at the Kayangan port, East Lombok in the following years, especially before Eid al-Fitr. The purpose of this study was to determine the calendar variation model that represents the sales volume pattern of class IVA vehicles so that the model can be used to predict the number of class IVA vehicles in ticket sales and to get the forecasting results for January 2019 – December 2019. Calendar variation is a recurring pattern with varying lengths of periods due to the influence of different calendars each year. Eid al-Fitr is one of the examples of the calendar variations that occur in Indonesia because Eid al-Fitr always has a shift in the Gregorian calendar. This shift is caused by the difference between one year in the Hijri calendar dan one year in the Gregorian calendar. These periodic changes give a calendar variation. Affected data by Eid al-Fitr such as the sales volume of the ticket at the ferry port will also have a calendar variation effect. Thus, to analyze the sales volume of tickets used ARIMA method with calendar variation effect or well known as calendar variation method. Based on the analysis, it is known that the significant dummy variable is D1 which is the variable of the month of Eid Al-Fitr. Then conducted ARIMA modeling of the dummy regression residuals. The best model then obtained by analysis, which is the calendar variation model that containing ARIMA (0,1,1)(1,0,0)12, all the parameters are significant and the residual assumption is fulfilled, which are normality test and white noise test. The Mean Absolute Percentage Error (MAPE) of the calendar variation model that containing ARIMA (0,1,1)(1,0,0)12 is 12,6% which means that the forecasting results can be trusted by 87,4%. [ABSTRACT FROM AUTHOR]