In forecasting, the design of an Artificial Neural Network (ANN) is a non-trivial task and choices incoherent with the problem could lead to instability of the network. So a Genetic Algorithm (GA) approach is used to find an optimal topology for the prediction. This paper presents a novel approach to Optimization of ANN topology that uses GA for the forecasting of Indian Stock Prices under Bombay Stock Exchange. After determining the optimum network determined by GA, forecasting of the stock prices is found by implementing MATLAB tool. The paper is organized as follows. The first Sectiondeals with the introduction to Genetic Algorithms; Section two reviews the literature on the optimization of neural network architectures and applications of genetic algorithms in doing so. Section three gives the proposed approach in the optimization of neural network architectures. Section four presents the experimental results by the methodology described in section three and followed by results and conclusion.