• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.983-991
• /
• 2017

High frequency time series are now prevalent in financial data. However, models need to be further developed to suit high frequency time series that account for intraday volatilities since traditional volatility models such as ARCH and GARCH are concerned only with daily volatilities. Due to $H{\ddot{o}}rmann$ et al. (2013), functional ARCH abbreviated as fARCH is proposed to analyze intraday volatilities based on high frequency time series. This article introduces fARCH to readers that illustrate intraday volatility configuration on the KOSPI and the Hyundai motor company based on the data with one minute high frequency.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• The Korean Journal of Applied Statistics
• /
• v.28 no.6
• /
• pp.1163-1170
• /
• 2015

Various computational methods for obtaining volatilities for financial time series are reviewed and compared with each other. We reviewed model based GARCH approach as well as the data based method which can essentially be regarded as a smoothing technique applied to the squared data. The method for high frequency data is focused to obtain the realized volatility. A hybrid method is suggested by combining the model based GARCH and the historical volatility which is a data based method. Korea stock prices are analysed to illustrate various computational methods for volatilities.

• The Korean Journal of Applied Statistics
• /
• v.34 no.4
• /
• pp.611-622
• /
• 2021

With a wide recognition that financial time series typically exhibits asymmetry patterns in volatility so called leverage effects, various asymmetric GARCH(1, 1) processes have been introduced to investigate asymmetric volatilities. A lot of researches have also been directed to non-stationary volatilities to deal with frequent high ups and downs in financial time series. This article is concerned with both asymmetric and non-stationary GARCH-type models. As a subsequent paper of Choi et al. (2020), we review various asymmetric and non-stationary GARCH(1, 1) processes, and in turn propose how to compare competing models using a parametric bootstrap methodology. As an illustration, Dow Jones Industrial Average (DJIA) is analyzed.

• The Korean Journal of Applied Statistics
• /
• v.35 no.3
• /
• pp.347-356
• /
• 2022

This article is concerned with asymmetric volatility models for financial time series. A generalization of standard single-threshold volatility model is discussed via multiple-threshold in which we specialize to twothreshold case for ease of presentation. An empirical illustration is made by analyzing S&P500 data from NYSE (New York Stock Exchange). For comparison measures between competing models, parametric bootstrap method is used to generate forecast distributions from which summary statistics of CP (Coverage Probability) and PE (Prediction Error) are obtained. It is demonstrated that our suggestion is useful in the field of asymmetric volatility analysis.

• The Korean Journal of Applied Statistics
• /
• v.22 no.2
• /
• pp.261-270
• /
• 2009

Current financial crisis triggered by shaky U.S. banking system adds to the emphasis on the importance of the volatility in controlling and understanding financial time series data. The ARCH and GARCH models have been useful in analyzing economic time series volatilities. In particular, multivariate GARCH(MGARCH, for short) provides both volatilities and conditional correlations between several time series and these are in turn applied to computations of hedge-ratio and VaR. In this short article, we try to assess various MGARCH models with respect to the back-testing performances in VaR study. To this end, 14 korean stock prices are analyzed and it is found that MGARCH outperforms rolling window, and BEKK and CCC are relatively conservative in back-testing performance.

• Communications for Statistical Applications and Methods
• /
• v.30 no.1
• /
• pp.75-94
• /
• 2023

The growing trend of cyber risk has put forward the importance of cyber risk management. Cyber risk is defined as an accidental or intentional risk related to information and technology assets. Although cyber risk is a subset of operational risk, it is reported to be handled differently from operational risk due to its different features of the loss distribution. In this study, we aim to detect the characteristics of cyber loss and find a suitable model by measuring value at risk (VaR). We use the loss distribution approach (LDA) and the time series model to describe cyber losses of financial and non-financial business sectors, provided in SAS^® OpRisk Global Data. Peaks over threshold (POT) method is also incorporated to improve the risk measurement. For the financial sector, the LDA and GARCH model with POT perform better than those without POT, respectively. The same result is obtained for the non-financial sector, although the differences are not significant. We also build a two-dimensional model reflecting the dependence structure between financial and non-financial sectors through a bivariate copula and check the model adequacy through VaR.

• The Korean Journal of Applied Statistics
• /
• v.20 no.3
• /
• pp.487-497
• /
• 2007

As is pointed out by Gourieroux (1997), the volatility effects in financial time series vary according to the signs of the return rates and therefore asymmetric Threshold-GARCH (TGARCH, henceforth) processes are natural extensions of the standard GARCH toward asymmetric volatility modeling. For preliminary detection of asymmetry in volatility, we suggest graphs of squared-log-returns for various financial time series including KOSPI, KOSDAQ and won-Euro exchange rate. Next, asymmetric TGARCH(1,1) model fits are provided in comparisons with standard GARCH(1.1) models.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.3
• /
• pp.809-815
• /
• 2007

Since Bollerslev(1986), the GARCH model has been popular in analysing the volatility of the financial time series. In real data analysis, practitioners conventionally put the normal assumption on the innovation random variables of the GARCH model, which is often violated. In this paper, we analyse the domestic financial data based on the GARCH(1,1) model and among existing normality tests, perform the Jarque-Bera test based on the residuals. It is shown that the innovation based on the GARCH(1,1) model dose not follow the normality assumption.

• Journal of Korean Institute of Industrial Engineers
• /
• v.36 no.2
• /
• pp.101-107
• /
• 2010

Among a variety of asset dynamics models in order to explain the common properties of financial underlying assets, parametric models are meaningful when their parameters are set reliably. There are two main methods from which we can obtain them. They are to use time-series data of an underlying price or the market option prices of the underlying at one time. Based on the Girsanov theorem, in the pure diffusion models, the parameters calibrated from the option prices should be partially equivalent to those from time-series underling prices. We call this phenomenon model consistency. In this paper, we verify that the two-state regime switching Black-Scholes model is superior in the sense of model consistency, comparing with two popular conventional models, the Black-Scholes model and Heston model.