We investigate how money market news headlines can be used to forecast intraday currency exchange rate movements. The innovation of the approach is that, unlike analysis based on quantifiable information, the forecasts are produced from text describing the current status of world financial markets, as well as political and general economic news. In contrast to numeric time series data textual data contains not only the effect (e.g., the dollar rises against the Deutschmark) but also the possible causes of the event (e.g., because of a weak German bond market). Hence improved predictions are expected from this richer input. The output is a categorical forecast about currency exchange rates: the dollar moves up, remains steady or goes down within the next one, two or three hours respectively. On a publicly available commercial data set the system produces results that are significantly better than random prediction. The contribution of this research is the smart modeling of the prediction problem enabling the use of content rich text for forecasting purposes.

Volatility modeling is the lifeline of the derivative- and asset-pricing evaluation process. As such, it is understandable that a voluminous literature has evolved to discuss the temporal dependencies in financial market volatility. Much of this literature has been directed at daily and lower frequencies using ARCH and stochastic volatility type models. With access to high frequency and ultra high-frequency databases, more recent research has been able to explain about fifty percent of the interdaily forecasts of latent volatility. Relying upon hourly intervals, the GARCH(1,1) results presented here are consistent with prior studies. However, this paper adds to the tools available for conducting volatility exploration by introducing an adaptive radial basis function neural network that significantly lowers overall prediction error while maintaining a high explanatory ratio. The newly formulated RBF implements a closed-form regularization parameter with Bayesian prior information. It is an algorithmic extension that will permit more accurate and insightful analyses to be performed on high frequency financial time series. Over the past decade, research efforts increased significantly in the area of modeling volatility behavior in capital market high frequency data. Obtaining accurate

Over the recent past, stylized facts have not yielded a synthesis regarding the predictability of returns for alternative investment assets such as hedge funds. Recent studies on alternative asset return predictability have added to the ambiguity. These studies suggest that classification prediction methods may dominate more traditional return-level prediction methodology. This paper examines the predictive accuracy of three alternate radial basis function neural networks when applied to the returns of thirteen Credit Swiss First Boston/Tremont (CSFB) hedge fund indices. We provide evidence that the Kajiji-4 RBF neural network dominates within the RBF topology in the prediction of hedge fund returns by both level and classification. The results also show that the Kajiji-4 method is capable of near perfect directional prediction.