S-transform based analysis for stock market volatility estimation

Abstract

Financial Time series analysis (FTSA) is concerned with theory and practice of asset valuation over time. Generally, FTSA is useful for forecasting the asset volatility. This paper proposes the discrete S-Transform technique driven by Gaussian kernel for the estimation of volatility in FTSA. S-Transform is found to be a better tool in finding the time frequency resolution so as to predict and estimate the risk and returns of financial market. S-Transform prediction on two different bench mark data sets namely, Standard & Poor(S&P) 500 and Dow Jones Industrial Average(DJIA) index clearly indicates its superiority for the prediction of short and long-term trends in stock markets.