Claim Missing Document
Check
Articles

Found 20 Documents
Search

Brown’s Weighted Exponential Moving Average Implementation in Forex Forecasting Seng Hansun; Subanar Subanar
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 15, No 3: September 2017
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v15i3.5410

Abstract

In 2016, a time series forecasting technique which combined the weighting factor calculation formula found in weighted moving average with Brown’s double exponential smoothing procedures had been introduced. The technique is known as Brown’s weighted exponential moving average (B-WEMA), as a new variant of double exponential smoothing method which does the exponential filter processes twice. In this research, we will try to implement the new method to forecast some foreign exchange, or known as forex data, including EUR/USD, AUD/USD, GBP/USD, USD/JPY, and EUR/JPY data. The time series data forecasting results using B-WEMA then be compared with other conventional and hybrid moving average methods, such as weighted moving average (WMA), exponential moving average (EMA), and Brown’s double exponential smoothing (B-DES). The comparison results show that B-WEMA has a better accuracy level than other forecasting methods used in this research.
H-WEMA: A New Approach of Double Exponential Smoothing Method Seng Hansun; Subanar Subanar
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 14, No 2: June 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v14i2.3096

Abstract

A popular smoothing technique commonly used in time series analysis is double exponential smoothing. Basically, it’s an improvement of simple exponential smoothing which does the exponential filter process twice. Many researchers had developed the technique, hence Brown’s double exponential smoothing and Holt’s double exponential smoothing. Here, we introduce a new approach of double exponential smoothing, called H-WEMA, which combines the calculation of weighting factor in weighted moving average with Holt’s double exponential smoothing method. The proposed method will then be tested on Jakarta Stock Exchange (JKSE) composite index data. The accuracy and robustness level of the proposed method will then be examined by using mean square error and mean absolute percentage error criteria, and be compared to other conventional methods.
SSA-based hybrid forecasting models and applications Winita Sulandari; Subanar Subanar; Suhartono Suhartono; Herni Utami; Muhammad Hisyam Lee; Paulo Canas Rodrigues
Bulletin of Electrical Engineering and Informatics Vol 9, No 5: October 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (587.132 KB) | DOI: 10.11591/eei.v9i5.1950

Abstract

This study attempted to combine SSA (Singular Spectrum Analysis) with other methods to improve the performance of forecasting model for time series with a complex pattern. This work discussed two modifications of TLSAR (Two-Level Seasonal Autoregressive) modeling by considering the SSA decomposition results, namely TLSNN (Two-Level Seasonal Neural Network) and TLCSNN (Two-Level Complex Seasonal Neural Network). TLSAR consisted of a linear trend, harmonic, and autoregressive component. In contrast, the two proposed hybrid approaches consisted of flexible trend function, harmonic, and neural networks. Trend and harmonic function were considered as the deterministic part identified based on SSA decomposition. Meanwhile, NN was intended to handle the nonlinearity relationship in the stochastic part. These two SSA-based hybrid models were contemplated to be more flexible than TLSAR and more applicable to the series with an intricate pattern. The experimental studies to the monthly accidental deaths in USA and daily electricity load Jawa-Bali showed that the proposed SSA-based hybrid model reduced RMSE for the testing data from that obtained by TLSAR model up to 95%.
Forecasting electricity load demand using hybrid exponential smoothing-artificial neural network model Winita Sulandari; Subanar Subanar; Suhartono Suhartono; Herni Utami
International Journal of Advances in Intelligent Informatics Vol 2, No 3 (2016): November 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v2i3.69

Abstract

Short-term electricity load demand forecast is a vital requirements for power systems. This research considers the combination of exponential smoothing for double seasonal patterns and neural network model. The linear version of Holt-Winter method is extended to accommodate a second seasonal component. In this work, the Fourier with time varying coefficient is presented as a means of seasonal extraction. The methodological contribution of this paper is to demonstrate how these methods can be adapted to model the time series data with multiple seasonal pattern, correlated non stationary error and nonlinearity components together. The proposed hybrid model is started by implementing exponential smoothing state space model to obtain the level, trend, seasonal and irregular components and then use them as inputs of neural network. Forecasts of future values are then can be obtained by using the hybrid model. The forecast performance was characterized by root mean square error and mean absolute percentage error. The proposed hybrid model is applied to two real load series that are energy consumption in Bawen substation and in Java-Bali area. Comparing with other existing models, results show that the proposed hybrid model generate the most accurate forecast
Simulation of queue with cyclic service in signalized intersection system Muhammad Dermawan Mulyodiputro; Subanar Subanar
International Journal of Advances in Intelligent Informatics Vol 1, No 1 (2015): March 2015
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v1i1.15

Abstract

The simulation was implemented by modeling the queue with cyclic service in the signalized intersection system. The service policies used in this study were exhaustive and gated, the model was the M/M/1 queue, the arrival rate used was Poisson distribution and the services rate used was Exponential distribution. In the gated service policy, the server served only vehicles that came before the green signal appears at an intersection. Considered that there were 2 types of exhaustive policy in the signalized intersection system, namely normal exhaustive (vehicles only served during the green signal was still active), and exhaustive (there was the green signal duration addition at the intersection, when the green signal duration at an intersection finished). The results of this queueing simulation program were to obtain characteristics and performance of the system, i.e. average number of vehicles and waiting time of vehicles in the intersection and in the system, as well as system utilities. Then from these values, it would be known which of the cyclic service policies (normal exhaustive, exhaustive and gated) was the most suitable when applied to a signalized intersection system
Estimating the function of oscillatory components in SSA-based forecasting model Winita Sulandari; Subanar Subanar; Suhartono Suhartono; Herni Utami; Muhammad Hisyam Lee
International Journal of Advances in Intelligent Informatics Vol 5, No 1 (2019): March 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v5i1.312

Abstract

The study of SSA-based forecasting model is always interesting due to its capability in modeling trend and multiple seasonal time series. The aim of this study is to propose an iterative ordinary least square (OLS) for estimating the oscillatory with time-varying amplitude model that usually found in SSA decomposition. We compare the results with those obtained by nonlinear least square based on Levenberg Marquardt (NLM) method. A simulation study based on the time series data which has a linear amplitude modulated sinusoid component is conducted to investigate the error of estimated parameters of the model obtained by the proposed method. A real data series was also considered for the application example. The results show that in terms of forecasting accuracy, the SSA-based model where the oscillatory components are obtained by iterative OLS is nearly the same with that is obtained by the NLM method.
Forecasting Interest Rate of Bank Indonesia Certificate Based on Multivariate Fuzzy Time Series Data Agus Maman Abadi; Subanar Subanar; Widodo Widodo; Samsubar Saleh
Jurnal ILMU DASAR Vol 11 No 2 (2010)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (86.122 KB)

Abstract

The aim of this research is to establish a model for forecasting interest rate of Bank Indonesia Certificate (BIC)based on six-factors one-order fuzzy time series data where the main factor is interest rate of BIC and thesecondary factors are interest rate of deposit, exchange rate, deposit supply, inflation rate and money supply.Steps to forecasting interest rate of BIC are based on Wang’s method. The result of this research is thatprediction of interest rate of BIC using multivariate fuzzy time series model has higher accuracy than that usingneural network method with average forecasting error 3.1256% and MSE value = 0.2699.
NON AUTOMATICALLY EXERCISED (NAE) EUROPEAN CAPPED CALL PRICING THEORY Subanar .; Suryo Guritno; Zanzawi S.; Abdurakhman .
Journal of the Indonesian Mathematical Society Volume 13 Number 2 (October 2007)
Publisher : IndoMS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22342/jims.13.2.69.215-221

Abstract

The objective of this paper is to present a methodology for deriving Black Scholes formulae via a simple lognormal distribution approach and introduce European capped non automatically exercise (NAE) call option pricing theory. DOI : http://dx.doi.org/10.22342/jims.13.2.69.215-221
EFFECTS OF CALENDAR VARIATIONS ON THE INDONESIA STOCK EXCHANGE: AN EMPIRICAL STUDY OF POTENTIAL STOCKS Putriaji Hendikawati; Subanar Subanar; Abdurakhman Abdurakhman; Tarno Tarno
STATMAT : JURNAL STATISTIKA DAN MATEMATIKA Vol 4, No 1 (2022)
Publisher : Math Program, Math and Science faculty, Pamulang University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/sm.v4i1.14921

Abstract

This study examines the effect of calendar variations on potential stocks on the Indonesia Stock Exchange. Calendar variations are observed in telecommunications, retail, food and cigarettes sub-sectors. The observed calendar variations are divided into two: the holiday effect, namely the effect of the month of Ramadan, the effect of the Eid al-Fitr holiday, and the effect of changes in the month of the Eid holidays; and the trading day effect, namely the effect of the day of the week and month of the year effects. ARIMA and ARIMAX model is used to see the effect of previous return data and the calendar variations on predicting stock returns. Descriptively, there is the effect of calendar variations due to Ramadan and Eid holidays and the influence of Monday and January effect. The existence of calendar variations does not apply equally to all types of stocks and to all observation time periods. The calendar variation tends to vary, does not form a clear pattern, does not consistently affect stock returns on the Indonesia Stock Exchange and is not statistically significant. Based on the analysis, it was found that the Monday effect and January effect are the most common phenomena in the Indonesian stock exchange.
PARAMETER INDEPENDENT FUZZY WEIGHTED k-NEAREST NEIGHBOR Mayawi, Mayawi; Subanar, Subanar
MEDIA STATISTIKA Vol 17, No 2 (2024): Media Statistika
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/medstat.17.2.162-172

Abstract

Parameter Independent Fuzzy Weighted k-Nearest Neighbor (PIFWkNN) as a classification technique developed by combining Success History based Parameter Adaptive Differential Evolution (SHADE) with Fuzzy k-Nearest Neighbor (FkNN), where this PIFWkNN does not state the optimization of weights and k values as two separate problems, but they’re combined into one and solved simultaneously by the SHADE algorithm. The steps for implementing the PIFWkNN method are explained, followed by its application to 10 different datasets, and then the accuracy is calculated. To see the consistency of the goodness of the classification of this method, the accuracy results are compared with the accuracy of the k-Nearest Neighbor (kNN), FkNN, and Weighted k-Nearest Neighbor (WkNN). The results show that the average accuracy of PIFWkNN, kNN, FkNN, and WkNN is 75.76%, 68.52%, 71.40% and 66.22% so PIFWkNN is higher than the three methods. Using the Wilcoxon Sign Rank (WSR) test also concluded that with a 95% confidence shows that every hypothesis had significant differences. Furthermore, it descriptively shows that the average rank of PIFWkNN is higher than the other. Thus, the PIFWkNN has higher accuracy than the kNN, FkNN, and WkNN.