Trading ebook Finance - Neural Prediction of Weekly Stock Market Index

One of the simplest models is that proposed by martin

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: ts to prove such a correlation. One of the simplest models is that proposed by Martin Zweig in [9], where some fundamental indicators such as the prime lending rate, the Federal reserve lending rate and the consumer price index as well some technical indicators such as the up/down volume ratio, bullish/bearish index based on newspaper advertisements and other momentum indicators are combined in a super model. The output of the supermodel is in terms of percent points which is used to obtain buy/sell signals so as to time the market in the long run. The model is shown to be able to predict most of the big bull and bear markets over the past years. Construction of such a model requires some amount of experience in dealing with the stock market, although once it is constructed, the functioning can be autonomous. In this project, an attempt is made to construct a neural network based model. The input data, which was kindly made available by Prof. Robert Porter includes the short term (3month) interest rate, the long term (10-year) interest rate charged by banks and the Standard and Poor’s 500 stock index (S&P 500)...
View Full Document

Ask a homework question - tutors are online