Download This PaperDoes the Predicating Power of Stock Return in Amman Stock Exchange (ASE) Improved by Using the Artificial Neural Networks ANN
EuroJournals Publishing, 2010
19 Pages Posted: 4 Jun 2020
Date Written: March 22, 2010
Abstract
The Efficient Market Hypothesis (EMH) emphasizes that the stocks already reflect all available information. If prices are determined rationally, then the only new information will cause them to change. Indeed, if stock movement were predictable, that would be damming evidence of stock market inefficiency because the ability to predicate prices would indicate that all available information was not already reflected in stock prices. The Capital Asset Pricing Model CAPM has long shaped the way for academics and practitioners to think about average returns and risk, then the three factor model of Fama and French (1992,1993) which specifies that stock risks are multidimensional (size and book-to-market value B/M).
For investors, the issue of market efficiency boils down to whether skilled investors can make consistent abnormal trading profits. The best test is to look at the performance of market professionals to see if they generate performance superior to that of the passive index that buys and holds the market,(Bodie & others 2008). One of the analytical techniques to outrun the market is the artificial neural networks ANN.
This article examines if the predicating power of stock return in Amman Stock Exchange had been proven by using more variables according to Fama and French model using the GMM and by using the Artificial Neural Networks AN. Also, it checks if the predicating power of stock return in Amman Stock Exchange had been proved by applying the two mentioned pricing models using ANN.
The results show that there is evidence that the predicating power improved in using more variables according to Fama and French model according to GMM regression but there was no accruing evidence according to ANN. Further more, the results show that using the ANN upon GMM regression on the two models CAPM and Fama. French model did not improve the predicting power of the stock returns on Amman Stock Return. We conclude that, the Artificial Neural Networks (ANN) aren't useful in predicting stock return in Amman Stock Exchange which means that there is no evidence of Amman stock inefficiency.
Keywords: Artificial Neural Networks ANN, Capital Asset Pricing Model CAPM, Fama and French Three Factor Model, Generalized Methods of Moments GMM
Suggested Citation: Suggested Citation