• Journal of the Korean Data and Information Science Society
• /
• v.11 no.1
• /
• pp.1-18
• /
• 2000

In this paper, we study several parameter estimation methods used for autoregressive processes and compare them in view of forecasting. The least square estimation, least absolute deviation estimation, robust estimation are compared through Monte Carlo simulations.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.325-326
• /
• 2021

LNG는 환경규제에 따라 화석에너지에서 친환경 재생에너지로 전환되는데 중요한 역할을 하는 에너지원이다. UN산하 세계해사기구(IMO)의 MARPOL협약에 따라 선박 황산화물 배출가스규제로 LNG추진 선박에 대한 수요가 증가되고 있을 뿐만 아니라 미국의 쉐일혁명으로 LNG를 수출함에 따라 공급의 변화가 급격하게 이뤄지고 있다. 과거 국가 주도의 프로젝트 성격이 강한 LNG 운송시장은 장기정기용선계약이 대부분이었으나 수요와 공급시장의 급격한 변화로 스팟시장의 중요성이 커지고 있다. 따라서 본 논문은 LNG 운송시장에서 시장참여자들의 스팟거래에 합리적인 의사결정이 이뤄지도록 과학적인 예측방법을 제시하고자 한다. LNG 스팟운임 예측에 기계학습모델 중 인공신경망 모델을 적용할 것이며 기존의 시계열분석 방법인 ARIMA모델과 비교하여 본문에서 제시된 모델의 예측성능의 우수성을 확인하였다. 본 논문은 LNG 스팟운임을 다룬 최초의 연구로서 학문적인 차별성이 기대된다.

• The Korean Journal of Applied Statistics
• /
• v.32 no.3
• /
• pp.405-421
• /
• 2019

Predicting how much energy to use is an important issue in society. However, it is more difficult to capture the usage characteristics of residential buildings than other buildings. This paper provides time series analysis methods for electricity consumption in a residential building. Temperature is closely related to electricity demand. An error correction model, which is a method of adjusting the error with time, is applied when a cointegration relation is established between variables. Therefore, we analyze data via ECMs with consideration of the temperature effect.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.59-66
• /
• 2023

The Golden Cross is commonly seen as a buy signal in financial markets, but its reliability for predicting stock price movements is limited due to market volatility. This paper introduces a time-invariant approach that considers the Golden Cross as a singular event. Utilizing LSTM neural networks, we forecast significant stock price changes following a Golden Cross occurrence. By comparing our approach with traditional time series analysis and using a confusion matrix for classification, we demonstrate its effectiveness in predicting post-event stock price trends. To conclude, this study proposes a model with a precision of 83%. By utilizing the model, investors can alleviate potential losses, rather than making buy decisions under all circumstances following a Golden Cross event.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.239-254
• /
• 2021

This paper studies time series analysis with estimation and forecasting for Korean COVID-19 confirmed cases, based on the approach of a heterogeneous autoregressive (HAR) model with two-piece t (TP-T) distributed errors. We consider HAR-TP-T time series models and suggest a step-by-step method to estimate HAR coefficients as well as TP-T distribution parameters. In our proposed step-by-step estimation, the ordinary least squares method is utilized to estimate the HAR coefficients while the maximum likelihood estimation (MLE) method is adopted to estimate the TP-T error parameters. A simulation study on the step-by-step method is conducted and it shows a good performance. For the empirical analysis on the Korean COVID-19 confirmed cases, estimates in the HAR-TP-T models of order p = 2, 3, 4 are computed along with a couple of selected lags, which include the optimal lags chosen by minimizing the mean squares errors of the models. The estimation results by our proposed method and the solely MLE are compared with some criteria rules. Our proposed step-by-step method outperforms the MLE in two aspects: mean squares error of the HAR model and mean squares difference between the TP-T residuals and their densities. Moreover, forecasting for the Korean COVID-19 confirmed cases is discussed with the optimally selected HAR-TP-T model. Mean absolute percentage error of one-step ahead out-of-sample forecasts is evaluated as 0.0953% in the proposed model. We conclude that our proposed HAR-TP-T time series model with optimally selected lags and its step-by-step estimation provide an accurate forecasting performance for the Korean COVID-19 confirmed cases.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.4
• /
• pp.807-817
• /
• 2014

This paper considers multivariate time series modelling of PM10 data in Korea collected from 2008 to 2011. We consider both temporal and spatial dependencies of PM10 by applying the sparse vector autoregressive (sVAR) modelling proposed by Davis et al. (2013). It utilizes the partial spectral coherence to measure cross correlation between different regions, in turn provides the sparsity in the model while balancing the parsimony of model and the goodness of fit. It is also shown that sVAR performs better than usual vector autoregressive model (VAR) in forecasting.

• KDI Journal of Economic Policy
• /
• v.14 no.1
• /
• pp.121-145
• /
• 1992

This paper examines characteristics of time series data related to the construction investment(stationarity and time series components such as secular trend, cyclical fluctuation, seasonal variation, and random change) and surveys predictibility, fitness, and explicability of independent variables of various models to build a short-term construction investment forecasting model suitable for current economic circumstances. Unit root test, autocorrelation coefficient and spectral density function analysis show that related time series data do not have unit roots, fluctuate cyclically, and are largely explicated by lagged variables. Moreover it is very important for the short-term construction investment forecasting to grasp time lag relation between construction investment series and leading indicators such as building construction permits and value of construction orders received. In chapter 3, we explicate 7 forecasting models; Univariate time series model (ARIMA and multiplicative linear trend model), multivariate time series model using leading indicators (1st order autoregressive model, vector autoregressive model and error correction model) and multivariate time series model using National Accounts data (simple reduced form model disconnected from simultaneous macroeconomic model and VAR model). These models are examined by 4 statistical tools that are average absolute error, root mean square error, adjusted coefficient of determination, and Durbin-Watson statistic. This analysis proves two facts. First, multivariate models are more suitable than univariate models in the point that forecasting error of multivariate models tend to decrease in contrast to the case of latter. Second, VAR model is superior than any other multivariate models; average absolute prediction error and root mean square error of VAR model are quitely low and adjusted coefficient of determination is higher. This conclusion is reasonable when we consider current construction investment has sustained overheating growth more than secular trend.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.268-272
• /
• 2012

현재 확률강우량을 산정할 때는 수문사상 자료계열이 정상성을 가지고 있다고 가정하고 산정하고 있다. 이는 경향성 검정을 통과하지 못한 비정상성을 가지는 자료계열이라 할지라도 이들 자료에 대해 해석을 할 수 있는 검증된 대안이 아직 없기 때문이다. 따라서 본 연구에서는 강우의 증가경향성이 존재하여 경향성 검정을 통과하지 못한 비정상성을 가지는 지역에 대해서 경향성을 고려한 확률강우량을 산정하고, 기존의 방법에 의해서 산정된 확률강우량과 비교해보았다. 그리고 현재까지의 강우량 자료를 시계열분석을 이용하여 미래 강우량 자료를 예측하고 확률강우량을 산정함으로써 시계열분석을 통한 확률강우량 산정과 경향성을 고려하여 산정된 확률강우량을 비교했다. 우선 실제로 우리나라의 강우의 패턴이 변화하고 있는지 확인하고, 변화의 양상이 뚜렷한 지점에 대해서 시계열분석을 이용하여 가까운 미래의 확률강우량을 산정하였다. 그 결과, 2010년에 비해서 2020년의 확률강우량이 4~15%정도 증가하였다. 다른 방법과 비교해본 결과, 약 5%의 편차를 보였다. 본 연구에서는 최종적으로 우리나라 강우관측소 61지점의 경향성을 판별하여 전국 지도에 등고선으로 나타내어 경향성을 고려해야 할 지역들은 분류하였고, 이 지도를 활용하여 확률강우량을 산정함으로써 수공구조물의 계획 및 설계, 하천관리, 수자원 계획 등에 활용하고 전체적인 설계 빈도 상향조정으로 발생되는 예산 낭비 방지와 홍수피해 저감에 도움이 되고자 한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.307-314
• /
• 2022

Recently, researches using deep learning-based models are being actively conducted to replace statistical-based time series forecast techniques to predict electric power demand. The result of analyzing the researches shows that the performance of the LSTM-based prediction model is acceptable, but it is not sufficient for long-term regional-wide power demand prediction. In this paper, we propose a WaveNet deep learning model to predict electric power demand 24-hour-ahead with temperature data in order to achieve the prediction accuracy better than MAPE value of 2% which statistical-based time series forecast techniques can present. First of all, we illustrate a delated causal one-dimensional convolutional neural network architecture of WaveNet and the preprocessing mechanism of the input data of electric power demand and temperature. Second, we present the training process and walk forward validation with the modified WaveNet. The performance comparison results show that the prediction model with temperature data achieves MAPE value of 1.33%, which is better than MAPE Value (2.33%) of the same model without temperature data.

• Journal of Korean Society of Transportation
• /
• v.20 no.4
• /
• pp.151-162
• /
• 2002

The object of this study is to develop an operating time prediction model for expressways using toll collection data. A Prediction model based on modular neural network model was developed and tested using real data. Two toll collection system(TCS) data set. Seoul-Suwon section for short range and Seoul-Daejeon section for long range, in Kyongbu expressway line were collected and analyzed. A time series analysis on TCS data indicated that operating times on both ranges are in reasonable prediction ranges. It was also found that prediction for the long section was more complex than that for the short section. However, a long term prediction for the short section turned out to be more difficult than that for the long section because of the higher sensitivity to initial condition. An application of the suggested model produced accurate prediction time. The features of suggested prediction model are in the requirement of minimum (3) input layers and in the ability of stable operating time prediction.