nan Suhartono

Two-level seasonal model based on hybrid ARIMA-ANFIS for forecasting short-term electricity load in Indonesia

The aim of this research is to develop a forecasting model for half-hourly electricity load in Java-Bali Indonesia by using two-level seasonal model based on hybrid ARIMA-ANFIS. This two-level forecasting model is developed based on the ARIMA model at the first level and ANFIS for the second level. The forecast accuracy is compared to the results of the individual approach of ARIMA and ANFIS. Data about half-hourly electricity load for Java-Bali on 1st January 2009 to 31st December 2010 period are used as case study. The results show that two-level seasonal hybrid ARIMA-ANFIS model with Gaussian membership function yields more accurate forecast values than individual approach of ARIMA and ANFIS model for predicting half-hourly electricity load, particularly up to 2 days ahead. This hybrid ARIMA-ANFIS model yields MAPE 1.78% for forecasting 7 days ahead and it is less than 2% as a benchmark value from Indonesian Electricity Company.

Introducing polynomial fuzzy time series

Using polynomial concept and non-liner optimization enhanced the performance of Chens 1996 and Yus 2005b methods as the two frequently used methods in fuzzy time series model. To this end, polynomial schemes were given to each fuzzy logical relationship groups that had been established through forecast process to establish non-linear optimization systems. The optimal solutions of this system were applied in corresponding steps of algorithms to obtain new weights. To validate model reliability and its effectiveness, the forecasts of two huge databases namely 5 years Taiwans stock index and 2010 load data of Power Supply Company in Johor Bahru in Malaysia were then exposed to the proposed model. Next, the forecasts were compared with real values in testing datasets. The evaluation of measuring criteria namely RMSEs and MAPEs showed that the proposed model could produce accurate forecast compared with the Chens and Yus method in fuzzy time series. The implication of this study is to generalize the results to other fuzzy time series models.

Improving TAIEX forecasting using fuzzy time series with Box–Cox power transformation

Box–Cox together with our newly proposed transformation were implemented in three different real world empirical problems to alleviate noisy and the volatility effect of them. Consequently, a new domain was constructed. Subsequently, universe of discourse for transformed data was established and an approach for calculating effective length of the intervals was then proposed. Considering the steps above, the initial forecasts were performed using frequently used fuzzy time series (FTS) methods on transformed data. Final forecasts were retrieved from initial forecasted values by proper inverse operation. Comparisons of the results demonstrate that the proposed method produced more accurate forecasts compared with existing FTS on original data.

A Weighted Fuzzy Integrated Time Series for Forecasting Tourist Arrivals

Literature reviews show that the most commonly studied fuzzy time series models for the purpose of forecasting is first order. In such approaches, only the first lagged variable is used when constructing the first order fuzzy time series model. Therefore, such approaches fail to analyze accurately trend and seasonal time series which is an important class in time series models. In this paper, a weighted fuzzy integrated time series is proposed in order to analyze trend and seasonal data and data are taken from tourist arrivals series. The proposed approach is based on differencing concept as data preprocessing method and weighted fuzzy time series. The order of this model is determined by utilizing graphical order fuzzy relationship. Four data sets about the monthly number of tourist arrivals to Indonesia via four main gates are selected to illustrate the proposed method and compare the forecasting accuracy with classical time series models. The results of the comparison in test data show that the weighted fuzzy integrated time series produces more precise forecasted values than those classical time series models.

Two levels ARIMAX and regression models for forecasting time series data with calendar variation effects

The aim of this research is to develop a calendar variation model for forecasting retail sales data with the Eid ul-Fitr effect. The proposed model is based on two methods, namely two levels ARIMAX and regression methods. Two levels ARIMAX and regression models are built by using ARIMAX for the first level and regression for the second level. Monthly men’s jeans and women’s trousers sales in a retail company for the period January 2002 to September 2009 are used as case study. In general, two levels of calendar variation model yields two models, namely the first model to reconstruct the sales pattern that already occurred, and the second model to forecast the effect of increasing sales due to Eid ul-Fitr that affected sales at the same and the previous months. The results show that the proposed two level calendar variation model based on ARIMAX and regression methods yields better forecast compared to the seasonal ARIMA model and Neural Networks.

Ensemble method based on ARIMA-FFNN for climate forecasting

Ensemble forecasting is one of relatively new modern methods for time series forecasting that employs averaging or stacking from the results of several methods. This paper focuses on the development of ensemble ARIMA-FFNN for climate forecasting by using averaging method. Two data about monthly rainfall in Indonesia, i.e. Wagir and Pujon region, are used as case study. Root mean of squares errors in training and testing datasets are used for evaluating the forecast accuracy. The results of ensemble ARIMA-FFNN are compared to one classical statistical method, i.e. individual ARIMA, and two modern statistical methods, namely individual FFNN and ensemble FFNN. The results show that ARIMA yields more accurate forecast in training datasets than other methods, whereas in testing datasets show that FFNN is the best method. Additionally, this conclusion in line with the results of M3 competition, i.e. modern methods or complex methods do not necessarily produce more accurate forecast than simpler one.

Multioutput Least Square SVR Based Multivariate EWMA Control Chart

Multioutput least square SVR has ability to remove serial correlation of process by mapping multivariate input space to multivariate output space. The aim of this research is to propose multioutput least squares SVR based multivariate EWMA control chart to monitor small change of multivariate autocorrelated process. VARMA model with additive and innovative outliers are generated to investigate the performance of proposed control chart. Simulation studies empirically show that multioutput least squares SVR based multivariate EWMA control chart detect either single or consecutive additive outlier takes place at different time in each variable accurately. On the contrary, single innovative outlier in each variable that occurs either at different time or at the same time is detected by multioutput least squares SVR based multivariate EWMA control chart as double out-of control signals.

Design of Experiment to Optimize the Architecture of Wavelet Neural Network for Forecasting the Tourist Arrivals in Indonesia

Wavelet Neural Network (WNN) is a method based on the combination of neural network and wavelet theories. The disadvantage of WNN is the lack of structured method to determine the optimum level of WNN factors, which are mostly set by trial and error. The factors affecting the performance of WNN are the level of MODWT decomposition, the wavelet family, the lag inputs, and the number of neurons in the hidden layer. This research presents the use of design of experiments for planning the possible combination of factor levels in order to get the best WNN. The number of tourist arrivals in Indonesia via Soekarno-Hatta airport in Jakarta and via Ngurah Rai airport in Bali is used as case study. The result shows that design of experiments is a practical approach to determine the best combination of WNN factor level. The best WNN for data in Soekarno-Hatta airport is WNN with level 4 of MODWT decomposition, Daubechies wavelet, and 1 neuron in the hidden layer. Whereas, the best WNN for data in Ngurah Rai airport is WNN with MODWT decomposition level 3 and using input proposed by Renaud, Starck, and Murtagh [11] and seasonal lag input addition.

Value-at-Risk Modeling on Stock Return with Exogenous Variables using ARMAX-GARCHX Approach

Stock is one of investment instrument that has high risk with possible high return or loss. Quantifying the risk associated with stock return is important work for financial institution to optimize their portfolios. To do that analysis, Value-at-Risk method becomes very popular and frequently applied recently. This work applies Value-at-Risk modeling using ARMAX-GARCHX approach that considers exogenous variables having significant effect to the volatility of return. Moreover, in this research the risk is estimated based on observations spanning in moving windows. There are three kinds of windows size, i.e. 250, 375, and 500 transaction days. Applying the proposed method to stock return of top four (in market share) companies in construction and building subsector at Indonesian stock exchange (IDX), at the period of tax amnesty, the empirical results show that the Value-at-Risk estimation using windows size 500 days perform better than ones obtained from the shorter windows

Hybrid ARIMAX Quantile Regression Model for Forecasting Inflow and Outflow of East Java Province

Most of inflow and outflow data in Indonesia are characterized by trend, seasonal, calendar variation, and heterogeneous variance. This study proposed hybrid ARIMAX Quantile Regression model for forecasting data that have trend, seasonal, calendar variation, and heterogeneous variance. There are two types of data that we used in this research, i.e. simulation and real data. The real data are monthly inflow and outflow of Bank Indonesia at East Java Province per currency for the period 2003 to December 2016. There are three types of ARIMAX Quantile Regression models with different predictors that be used for forecasting both data. The results show that hybrid ARIMAX Quantile Regression model can capture accurately all patterns in the data. Moreover, this hybrid model yield better forecast than individual ARIMAX model at 8 of 14 currencies of inflow and outflow data in East Java Province. Thus, based on forecast accuracy criteria, i.e. RMSE, MAE and MdAE, it could be concluded that hybrid ARIMAX Quantile Regression tend to give better forecast than other individual method.