Abstract: Forecasting accuracy is the most important factor in selecting any forecasting methods. Research efforts in improving the accuracy of forecasting models are increasing since the last decade. The appropriate stock selections those are suitable for investment is a difficult task. The key factor for each investor is to earn maximum profits on their investments. In stock market two opposite teams are involves in any type of transaction in which they exchange stocks from buyer to seller. Patterns of the stock market are of non uniform nature. Holding and vending of shares in stock market is done by the consideration of some decision making algorithms. Main Objective of work is to development of a Time-Series neural network that achieved a highest percent probability of predicting a market rise and market drop as compare to existing methods. So to produce the consistent and accurate results, there is need to produce the new modified algorithm. This new enhanced and modified algorithm produces the predictions in timely manner with appropriate accuracy.

Keywords: Neural Network, Forecasting, Stock Market, Time Series, Data Mining.