• The Korean Journal of Applied Statistics
• /
• v.18 no.3
• /
• pp.639-654
• /
• 2005

The Lee and Carter method has widely used to forecast mortality because of the simple structure of model and the stable forecasting. The Lee and Carter method, however, also has limitations. The assumption of the rate of decline in mortality at each age remaining invariant over time has been violated in several decades. And, there is no way to include covariates in the model for better forecasts. Here we introduce Park, Choi and Kim method to make up for Lee and Carter's weak points by using two random processes. We discuss structural features of two methods. furthermore, for each method, we forecast life expectancy for 2005 to 2050 using South Korea data and compare the results.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.193-203
• /
• 2016

This paper forecasts electricity demand as a critical element of a demand management system in Smart Grid environment. We present a prediction method of using a combination of predictive values by time series clustering. Periodogram-based normalized clustering, predictive analysis clustering and dynamic time warping (DTW) clustering are proposed for time series clustering methods. Double Seasonal Holt-Winters (DSHW), Trigonometric, Box-Cox transform, ARMA errors, Trend and Seasonal components (TBATS), Fractional ARIMA (FARIMA) are used for demand forecasting based on clustering. Results show that the time series clustering method provides a better performances than the method using total amount of electricity demand in terms of the Mean Absolute Percentage Error (MAPE).

• Atmosphere
• /
• v.31 no.3
• /
• pp.341-359
• /
• 2021

This technical note introduces the new Korea Meteorological Administration (KMA) Global Seasonal forecasting system version 6 (GloSea6) to provide a reference for future scientific works on GloSea6. We describe the main areas of progress and improvements to the current GloSea5 in the scientific and technical aspects of all the GloSea6 components - atmosphere, land, ocean, and sea-ice models. Also, the operational architectures of GloSea6 installed on the new KMA supercomputer are presented. It includes (1) pre-processes for atmospheric and ocean initial conditions with the quasi-real-time land surface initialization system, (2) the configurations for model runs to produce sets of forecasts and hindcasts, (3) the ensemble statistical prediction system, and (4) the verification system. The changes of operational frameworks and computing systems are also reported, including Rose/Cylc - a new framework equipped with suite configurations and workflows for operationally managing and running Glosea6. In addition, we conduct the first-ever run with GloSea6 and evaluate the potential of GloSea6 compared to GloSea5 in terms of verification against reanalysis and observations, using a one-month case of June 2020. The GloSea6 yields improvements in model performance for some variables in some regions; for example, the root mean squared error of 500 hPa geopotential height over the tropics is reduced by about 52%. These experimental results show that GloSea6 is a promising system for improved seasonal forecasts.

• Journal of the Korean Solar Energy Society
• /
• v.39 no.4
• /
• pp.41-54
• /
• 2019

The proportion of solar photovoltaic power generation has steadily increased in the power trade market. Solar energy forecast is highly important for the stable trade of volatile solar energy in the existing power trade market, and it is necessary to identify accurately any forecast error according to the forecast lead time. This paper analyzes the latest study trend in solar energy forecast overseas and presents a consistent comparative assessment by adopting a single statistical variable (nRMSE) for forecast errors according to lead time and forecast technology.

• Asia-Pacific Journal of Business
• /
• v.14 no.1
• /
• pp.149-169
• /
• 2023

Purpose - The main purpose of this study is to develop the stress test model for Korean banks by exploring the optimal Monte Carlo simulation and BIS forecasting model. Design/methodology/approach - This study selects 15 Korean banks as sample financial firms and collects relevant 76 quarterly data for the period between year 2000 and 2018 from KRX(Korea Excange), Bank of Korea, and FnGuide. The Regression analysis, Unit-root test, and Monte Carlo simulation are hired to analyze the data. Findings - First, most of the sample banks failed to keep 8% BIS ratio for the adverse and severely Adverse Scenarios, implying that Korean banks must make every effort to realize better BIS ratios under adverse market conditions. Second, we suggest the better Monte Carlo simulation model for the Korean banks by finding that the more appropriate volatility should be different depending on variables rather than simple two-sigma which has been used in the previous studies. Third, we find that the stepwise regression model is better fitted than simple regression model in forecasting macro-economic variables for the BIS variables. Fourth, we find that, for the more robust and significant statistical results in designing stress tests, Korean banks are required to construct more valid time-series and cross-sectional data-base. Research implications or Originality - The above results all together show that the optimal volatility in designing optimal Monte Carlo simulation varies depending on the country, and many Korean banks fail to pass sress test under the adverse and severely adverse scenarios, implying that Korean banks need to make improvement in the BIS ratio.

• The Korean Journal of Applied Statistics
• /
• v.37 no.4
• /
• pp.499 -508
• /
• 2024

In this paper, we investigate hierarchical time series forecasting that adhere to a hierarchical structure when deriving predicted values by analyzing segmented data as well as aggregated datasets. The occurrences of food poisoning by a specific pathogen are analyzed using zero-inflated Poisson regression models and negative binomial regression models. The occurrences of major, miscellaneous, and overall food poisoning are analyzed using Poisson regression models and negative binomial regression models. For hierarchical time series forecasting, the MinT estimation proposed by Wickramasuriya et al. (2019) is employed. Negative predicted values resulting from hierarchical adjustments are adjusted to zero, and weights are multiplied to the remaining lowest-level variables to satisfy the hierarchical structure. Empirical analysis revealed that there is little difference between hierarchical and non-hierarchical adjustments in predictions based on pathogens. However, hierarchical adjustments generally yield superior results for predictions concerning major, miscellaneous, and overall occurrences. Without hierarchical adjustment, instances may occur where the predicted frequencies of the lowest-level variables exceed that of major or miscellaneous occurrences. However, the proposed method enables the acquisition of predictions that adhere to the hierarchical structure.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.95-101
• /
• 2008

Modeling of stock prices forecast has been considered as one of the most difficult problem to develop accurately since stock prices are highly correlated with various environmental conditions including economics and political situation. In this paper, we propose a agent system approach to predict Korea Composite Stock Price Index (KOSPI) using neural network and statistical methods. To minimize mean of prediction error and variation of prediction error, agent system includes sub-agent modules for feature extraction, variables selection, forecast engine selection, and forecasting results analysis. As a first step to develop agent system for KOSPI forecasting, twelve economic indices are selected from twenty two basic standard economic indices using principal component analysis. From selected twelve economic indices, prediction model input variables are chosen again using best-subsets regression method. Two different types data are tested for KOSPI forecasting and the Prediction results showed 11.92 points of root mean squared error for consecutive thirty days of prediction. Also, it is shown that proposed agent system approach for KOSPI forecast is effective since required types and numbers of prediction variables are time-varying, so adaptable selection of modeling inputs and prediction engine are essential for reliable and accurate forecast model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.4
• /
• pp.443-463
• /
• 2024

This study sought to improve the accuracy of precipitation prediction by utilizing monthly precipitation data for each region over the past 30 years. Using statistical models (ARIMA, SARIMA) and deep learning models (LSTM, GBM), we learned monthly precipitation data from 1983 to 2012 in Gangneung, Gwangju, Daegu, Daejeon, Busan, Seoul, Jeju, and Chuncheon. Based on this, monthly precipitation was predicted for 10 years from 2013 to 2022. As a result of the prediction, most models accurately predicted the precipitation trend, but showed a tendency to underpredict the actual precipitation. To solve these problems, appropriate models were selected for each region and season. The LSTM model showed suitable results in Gangneung, Gwangju, Daegu, Daejeon, Busan, Seoul, Jeju, and Chuncheon. When comparing forecasting power by season, the SARIMA model showed particularly suitable forecasting performance in winter in Gangneung, Gwangju, Daegu, Daejeon, Seoul, and Chuncheon. Additionally, the LSTM model showed higher performance than other models in the summer when precipitation is concentrated. In conclusion, closely analyzing regional and seasonal precipitation patterns and selecting the optimal prediction model based on this plays a critical role in increasing the accuracy of precipitation prediction.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.4
• /
• pp.615-627
• /
• 2009

In micro marketing promotion, it is important to know the behavior of customers. In this study we are interested in the forecasting of repurchase of customers from customers' behavior. By analyzing the cosmetic transaction data we derive some variables which play an important role in the knowledge of the customers' behavior and in the modeling of repurchase. As modeling tools we use the decision tree, logistic regression and neural network model. Finally we decide to use the decision tree as a final model since it yields the smallest RASE (root average squared error) and the greatest correct classification rate.

• Journal of Korea Water Resources Association
• /
• v.49 no.9
• /
• pp.761-771
• /
• 2016

The GloSea5 (Global Seasonal forecasting system version 5) is provided and operated by the KMA (Korea Meteorological Administration). GloSea5 provides Forecast (FCST) and Hindcast (HCST) data and its horizontal resolution is about 60km ($0.83^{\circ}{\times}0.56^{\circ}$) in the mid-latitudes. In order to use this data in watershed-scale water management, GloSea5 needs spatial-temporal downscaling. As such, statistical downscaling was used to correct for systematic biases of variables and to improve data reliability. HCST data is provided in ensemble format, and the highest statistical correlation ($R^2=0.60$, RMSE = 88.92, NSE = 0.57) of ensemble precipitation was reported for the Yongdam Dam watershed on the #6 grid. Additionally, the original GloSea5 (600.1 mm) showed the greatest difference (-26.5%) compared to observations (816.1 mm) during the summer flood season. However, downscaled GloSea5 was shown to have only a -3.1% error rate. Most of the underestimated results corresponded to precipitation levels during the flood season and the downscaled GloSea5 showed important results of restoration in precipitation levels. Per the analysis results of spatial autocorrelation using seasonal Moran's I, the spatial distribution was shown to be statistically significant. These results can improve the uncertainty of original GloSea5 and substantiate its spatial-temporal accuracy and validity. The spatial-temporal reproducibility assessment will play a very important role as basic data for watershed-scale water management.