Forecasting Financial Markets Using Neural Networks: An - download pdf or read online

By Jason E. Kutsurelis

ISBN-10: 1423557301

ISBN-13: 9781423557302

This examine examines and analyzes using neural networks as a forecasting device. in particular a neural network's skill to foretell destiny tendencies of inventory marketplace Indices is validated. Accuracy is in comparison opposed to a conventional forecasting strategy, a number of linear regression research. eventually, the chance of the model's forecast being right is calculated utilizing conditional chances. whereas purely in brief discussing neural community thought, this study determines the feasibility and practicality of utilizing neural networks as a forecasting software for the person investor. This learn builds upon the paintings performed by means of Edward Gately in his publication Neural Networks for monetary Forecasting. This study validates the paintings of Gately and describes the advance of a neural community that completed a 93.3 percentage chance of predicting a marketplace upward push, and an 88.07 percentage likelihood of predicting a industry drop within the S&P500. It was once concluded that neural networks do have the aptitude to forecast monetary markets and, if thoroughly proficient, the person investor may gain advantage from using this forecasting software.

Show description

Read Online or Download Forecasting Financial Markets Using Neural Networks: An Analysis of Methods and Accuracy PDF

Similar networking books

Read e-book online Cisco IOS in a Nutshell: A Desktop Quick Reference for IOS PDF

Cisco routers are available in all sizes and shapes and just about all of them, from the smallest to the biggest, run the IOS working process. IOS is an incredibly strong and intricate working method, with an equivalently advanced configuration language. there are lots of instructions, with many innovations, and if something is configured incorrectly, the total corporation may well locate itself offline.

Get Strategy and Governance of Networks: Cooperatives, PDF

The e-book emphasizes study in economics and administration of networks as an interdisciplinary box via supplying new theoretical views and offering new empirical effects on strategic and governance constitution concerns in cooperatives, franchising networks, alliances, joint ventures and enterprise capital family.

Download e-book for kindle: Networking und Projektorientierung: Gestaltung des Wandels by Henning Balck (auth.), Dipl.-Ing. Henning Balck (eds.)

Moderne Unternehmen erhöhen ihre Wettbewerbsfähigkeit durch die Umgestaltung ihrer organization. In solchen Wandlungsprozessen bilden Projektorientierung und Networking wesentliche Eckpfeiler. Die Autoren, anerkannte Wissenschaftler und Unternehmenspraktiker, sind jedoch Gegner technokratischer Gewaltakte.

Additional info for Forecasting Financial Markets Using Neural Networks: An Analysis of Methods and Accuracy

Sample text

The actual and predicted values from both the Close and Percent networks were placed into one spreadsheet. The predicted closing value of the S&P500 index was calculated using the predicted % change provided by the Percent Network. This allowed comparison of a single type of data between both networks. The two predicted closing values where 25 compared graphically and statistically. This completed the neural network portion of the research. A more traditional statistical forecasting tool is regression analysis.

If the dates were not equal, Excel placed a 1 in a row. This function was copied down the entire data set and then summed at the bottom. A sum of zero represented no date integrity discrepancies. A sum of anything greater than zero indicated that a date discrepancy existed. The sum was zero for all indexes 19 with the exception of *CRB. Within *CRB it was found that one trading day was missing. Instead of deleting the index, the trading day was added. The average closing value of the day proceeding and following the missing day was chosen to represent the missing day.

Bayes’ Theorem states that a probability depends upon the environment in which it is based. A conditional probability is stated as given X what is the probability of Y or P Y X . First the researcher had to find something that could easily be identified in the environment. It would be tedious to try and calculate probabilities for individual S&P500 closing values or individual percent changes. However, one could calculate the number of times the market rose or fell; this is potentially enough information for the investor.

Download PDF sample

Forecasting Financial Markets Using Neural Networks: An Analysis of Methods and Accuracy by Jason E. Kutsurelis

by John

Rated 4.21 of 5 – based on 13 votes