Content area

Full Text

 
Headnote

ABSTRACT

This study performs and compares the accuracy of Simplified Ohlson model and Refined Ohlson model using Artificial Neural Network (ANN) for valuing bank stocks. Prediction accuracy measuring procedures are used to compare the performance of these models. This study also focused on comparing the predictive power of Simplified Ohlson Model & Refined Ohlson Model (using ANN) using coefficient of determination. The outcomes of predictions are discussed to know the power of Artificial Neural Network. The results of empirical analysis support that Refined Ohlson model using ANN can be used as a valuation tool to provide better and more accurate estimation of equity stock prices of banks.

Key words: Ohlson Stock Valuation Model, Prediction Accuracy, Artificial Neural Network.

(ProQuest: ... denotes formulae omitted.)

INTRODUCTION

Prediction of bank stock price is generally believed to be a very difficult task. Artificial Neural Networks (ANN) have been used in stock market prediction during the last decade. An ANN model is a computer model whose architecture essentially mimics the learning capability of the human brain.The processing elements of an ANN resemble the biological structure of neurons and the internal operation of a human brain. In some applications it has been specified that artificial neural networks have limitations for learning the data patterns or that they may perform inconsistently and become unpredictable because of the complex financial data used. In US Stock market, artificial neural networks are mostly used in predicting financial failures. There has been no specific research for prediction of stock market values in Indian stock market using Artificial neural network. The main objective of this study is to enhance, revise and refine the Ohlson valuation model for Indian bank stocks (included in the BSE Bankex) using artificial neural network. This will help to improve the accuracy for valuing bank stocks in Indian Stock Market.

REVIEW OF LITERATURE

Karl Nygren ( 2004 ) study found that error correction neural network could be successfully used as decision support in a real trading situation and proved that it is successful in stock market. According to Mahdi Pakdaman Naeini (2010), application of Multi Layer Perceptron (MLP) neural network model is more promising in predicting stock value changes rather than Elman recurrent network and linear regression methods. Dase R.K (2010)...

Show less