This paper attempts to enhance the stock selection process by employing value-based investment criteria to select stocks in the Indian stock market. Neural networks are used to identify stocks for the portfolio which are likely to outperform the market, given the fundamental accounting information of stocks. The analysis uses ten financial ratios and employs a backpropagation neural network to select the stocks with the highest predicted returns in the Indian stock market. The BSE 500 index of the Bombay Stock Exchange constitutes the sample, and the study is conducted for the period 1995-2005. The returns obtained from the equally weighted portfolio formed by the stocks selected by neural networks significantly outperform the benchmark index, the BSE Sensex. The analysis also establishes the existence of a value premium in Indian stock market and utility of fundamental characteristics as price predictors.
