Trading ebook Finance - Neural Prediction of Weekly Stock Market Index

A recurrent network such as an elman net can be

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ecurrent network such as an Elman net can be applied so that the effect of the interest rates on the stock index prior to the data used can also be accounted for. Thus, a history or integral effect can be obtained using a recurrent network. • Even if a recurrent network is used, some delay will have to be assumed for using the interest rates. The easiest case would be to use current interest rates without any delay 16 • and allow the training to establish the actual delay. There is a lot of scope for work with regard to the choice of the delay in the interest rates. For using this technique in practice, a trading mechanism based on the predictions of the network needs to be established which will give buy/sell signals and will maximize profit without increasing the number of trades by a large number. 6. References [1] Black, F. and Scholes, M., “The pricing of Options and Corporate Liabilities,” Journal of Political Economy, vol. 81, no. 3, May-June 1973. [2] Azoff, E. M., Neural network time series forecasting of financial markets, Wiley, New York, 19...
View Full Document

This note was uploaded on 07/20/2012 for the course ECON 203 taught by Professor Girishdev during the Spring '12 term at Indian Institute of Technology, Kharagpur.

Ask a homework question - tutors are online