인공신경망-금융시계열 모형을 이용한 KOSPI 200주가지수의 변동성 예측

Abstract

As the index option market grows recently, many analysts and investors become interested in forecasting the volatility of KOSPI 200 Index to achieve portfolios objectives from the points of financial risk management and asset valuations. Therefore, for recent decades, many papers have tried to forecast volatilities more accurately using financial time series models and ANN(Artificial Neural Network) model. Historically, many papers about volatility forecasting have concentrated on the comparison between forecasting models, but this paper focuses on improving the predictive power of models by integrating ANN and financial time series models. For this purpose, this paper proves that financial time series models, GARCH, outperforms existing ANN in forecasting the direction of volatility and that ANN model excels GARCH in reducing the precision error of the forecasted volatility by analyzing KOSPI 200 index time series data. Hence, this paper tries to integrate the financial time series models and ANN to improve the predictive power within the framework of the precision and the direction of the volatility of KOSPI 200 index. Then, this paper tries to integrate ANN with the other financial time series models such as, EGARCH and EWMA and find which integrated model outperforms most in volatility forecasting by using MAE(Mean Absolute Error) and Hit ratio analysis. Conclusively, this paper suggests the merits of integration process and the need of integrated models to enhance the predictive power.