Stock Price Prediction using LSTM

The movement of stock prices is non-linear and complicated. In this study, we compared analyzed various neural network forecasting methods based on real problems related to price demand forecasting. We ultimately selected the LSTM (Long Short-Term Memory) [1] as traditional RNN’s long-term reliance improved by LSTM, which substantially enhances prediction accuracy stability. practicality method pertinence model are then inspected, final conclusions drawn through a detailed examination forecasts using networks optimized RNN algorithms. Past information has proven be extremely predominant investors basis for financing resolution. Previous studies have used open close vital predictors financial markets, but utmost highs lows may provide extra regarding future actions. Hence, two representative indexes Indian market were survey, main data collected from them open, closed, lowest, highest, date, everyday transaction size. outcome shows that few restraints, including forecast time lag, you can use attention level foretell prices. Its primary idea analyze historical find role series digging deeper into its central rules.