Abstract:
The stock market is known for its non-liner, unpredictable and dynamic nature. It has always been a hot and profitable place to learn. In the area of financial forecasting and forecasting, in-depth course applications have been shown to improve accuracy and yield better results. Machine learning-based stock prediction allows to forecast a company’s stock value in the future. The whole point of stock market forecasting is to generate revenue. In this project we have used Long-Short Term Memory architecture for analysis and development of a stock exchange predictor. The suggested approach is thorough since it incorporates stock market data pre-processing and specialized reading algorithm to forecast stock market prices. Our goal is to use an effective prediction model and produce accurate results with a very low percentage of error.
