The study proposes and a family of regime switching GARCH neural network models to model volatility. The proposed MS-ARMA-GARCH-NN models allow MS type regime switching in both the conditional mean and conditional variance for time series and further augmented with artificial neural networks to...

Common indicators of business and monetary conditions, the lagged mutual fund- risk premium and the market- risk premium are used to predict mutual fund returns for a time horizon of one-day. In isolation, each of the four predictors significantly forecast mutual-fund returns from April 2008 to...

Forecasting volatility models typically rely on either daily or high frequency (HF) data and the choice between these two categories is not obvious. In particular, the latter allows to treat volatility as observable but they suffer from many limitations. HF data feature microstructure problem,...

This paper investigates whether pre-specified macroeconomic factors can adequately proxy for the pervasive influences in stock returns, within the context of macroeconomic linear factor models motivated by the multifactor Arbitrage Pricing Theory (APT). Variation in stock returns can be...

In this study, we present a combinatory chaos analysis of daily wavelet-filtered (denoised) S&P 500 returns (2000–2020) compared with respective surrogate datasets, Brownian motion returns and a Lorenz system realisation. We show that the dynamics of the S&P 500 return series consist of an...

Investors rely on the stock-bond correlation for a variety of tasks, such as forming optimal portfolios, designing hedging strategies, and assessing risk. Most investors estimate the stock-bond correlation simply by extrapolating the historical correlation of monthly returns and assume that this...

This paper develops a method to improve the estimation of jump variation using high frequency data with the existence of market microstructure noises. Accurate estimation of jump variation is in high demand, as it is an important component of volatility in finance for portfolio allocation,...

Forecasting volatility models typically rely on either daily or high frequency (HF) data and the choice between these two categories is not obvious. In particular, the latter allows to treat volatility as observable but they suffer from many limitations. HF data feature microstructure problem,...

Forecasting-volatility models typically rely on either daily or high frequency (HF) data and the choice between these two categories is not obvious. In particular, the latter allows to treat volatility as observable but they suffer of many limitations. HF data feature microstructure problem,...

A time-series basis decomposition and trend extraction technique known as Empirical Mode Decomposition (EMD), designed for multi-scale time-frequency decomposition in non-stationary time-series settings, will be combined with Regularised Covariance Regression (RCR) methods to produce a framework...