Trading ebook Finance - Neural Prediction of Weekly Stock Market Index

Case 1 bull run since jan 1994 fig 9 shows the

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: he results obtained are analyzed below. Case 1: Bull run since Jan, 1994 Fig. 9 shows the normalized training and test data of the S&P500 index, while Fig. 10 shows the normalized training and test data for the interest rates. The data starts from the 850th data point and the training data is of length 275 while the test data has a length of 50 weeks. It can be seen that the long term interest rate is rising for most part of the bull run (testing data) except at the end, while the short term rate delayed by 20 weeks is rising initially and then constant. This change from rising to constant is expected to have some effect on the market. However, in this region the main effect is expected to come from the market momentum itself, as analyzed by economists elsewhere [9]. Test results Fig. 11 shows the test results for this case. The testing is done using the trained network and the output for each week is compared with the desired output. It can be seen from the figure that the network is able to predict the...
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