Monitoring Volatility Change for Time Series Based on Support Vector Regression

Abstract

This paper considers monitoring an anomaly from sequentially observed time series with heteroscedastic conditional volatilities based on the cumulative sum (CUSUM) method combined with support vector regression (SVR). The proposed online monitoring process is designed to detect a significant change in volatility of financial time series. The tuning parameters are optimally chosen using particle swarm optimization (PSO). We conduct Monte Carlo simulation experiments to illustrate the validity of the proposed method. A real data analysis with the S&P 500 index, Korea Composite Stock Price Index (KOSPI), and the stock price of Microsoft Corporation is presented to demonstrate the versatility of our model.

One‐class classification‐based monitoring for the mean and variance of time series

“…These strategies are widely used in statistical monitoring processes. Refer to Gombay and Serban 29 and Lee et al 30 . When $$Z_i$$ is an iid standard normal random variable, $$Z_i$$ can be considered an outlier if $$|Z_i|>A$$ for some $$A>0$$.…”

Monitoring the Zero-Inflated Time Series Model of Counts with Random Coefficient

“…While the violation of this major assumption seriously affects the monitoring performance of the charts (Harris and Ross [ 34 ], Triantafyllopoulos and Bersimis [ 35 ], Albarracin, Alencar and Ho [ 36 ]). Some authors have studied the performance of CUSUM charts for some integer-valued models (Weiß and Testik [ 23 ], Weiß and Testik [ 24 ], Yontay, Weiß, Testik and Bayindir [ 25 ], Rakitzis, Weiß and Castagliola [ 26 ], Li, Wang and Sun [ 27 ], Lee and Kim [ 37 ], Lee, Kim and Kim [ 38 ]).…”

Monitoring parameter change for bivariate time series models of counts

“…Taking the approach of Gombay and Serban ( 2009 ) and (Huh et al, 2017 ) developed a monitoring process for Poisson INGARCH models, and Lee and Kim ( 2020 ) redesigned it to react more sensitively to both decrease and increase in mean and variance and developed a robust monitoring process for general INGARCH models. Lee et al ( 2020 ) later adopted this scheme for monitoring a significant volatility change of GARCH time series using support vector regression. All these works handle not only the case of known parameters but also the situation that the parameter estimates are plugged into the monitoring processes, wherein the control limit is determined asymptotically on the basis of limit theorems.…”