Neural networks have been shown to be a promising tool for forecasting financial time series. Several design factors significantly impact the accuracy of neural network forecasts. These factors include selection of input variables, architecture of the network, and quantity of training data. The questions of input variable selection and system architecture design have been widely researched, but the corresponding question of how much information to use in producing high-quality neural network models has not been adequately addressed. In this paper, the effects of different sizes of training sample sets on forecasting currency exchange rates are examined. It is shown that those neural networks---given an appropriate amount of historical knowledge ---can forecast future currency exchange rates with 60 percent accuracy, while those neural networks trained on a larger training set have a worse forecasting performance. In addition to higher-quality forecasts, the reduced training set sizes reduce development cost and time.

Contents i Table of Contents 1. INTRODUCTION TO ARTIFICIAL INTELLIGENCE AND ARTIFICIAL NEURAL NETWORKS .......................................................................................................................................... 2 1.1 INTRODUCTION ........................................................................................................................... 2 1.2 ARTIFICIAL INTELLIGENCE .......................................................................................................... 2 1.3 ARTIFICIAL INTELLIGENCE IN FINANCE ....................................................................................... 4 1.3.1 Expert System ................................................................................................................... 4 1.3.2 Artificial Neural Networks in Finance..........................................

Financial operators have today access to an extremely large amount of data, both quantitative and qualitative, real-time or historical and can use this information to support their decision-making process. Quantitative data are largely processed by automatic computer programs, often based on artificial intelligence techniques, that produce quantitative analysis, such as historical price analysis or technical analysis of price behaviour. Differently, little progress has been made in the processing of qualitative data, which mainly consists of financial news articles from financial newspapers or on-line news providers. As a result the financial market players are overloaded with qualitative information which is potentially extremely useful but, due to the lack of time, is often ignored. The goal of this work is to reduce the qualitative data-overload of the financial operators. The research involves the identification of the information in the source financial articles which is relevant ...

this paper we introduce a rank measure that takes into accountalargenumber of securities and grades them according to the relative returns. It turns out that this rank measure, besides being more related to a real trading situation, is more predictable than the individual returns. The rank is predicted with a linear model and the empirical results show 63% hit rate for the sign of daily threshold-selected 1-day predictions

Most models for prediction of the stock market focus on individual securities. In this paper we introduce a rank measure that takes into account a large number of securities and grades them according to the relative returns. It turns out that this rank measure, besides being more related to a real trading situation, is more predictable than the individual returns. The ranks are predicted with percepttons with a step function for generation of trading signals. A learning decision support system for stock picking based on the rank predictions is constructed.

Abstract not found

Abstract not found