Investigating the Effect of Noise Elimination on LSTM Models for Financial Markets Prediction Using Kalman Filter and Wavelet Transform

Predicting financial markets is of particular importance for investors who intend to make the most profit. Analysing reasonable and precise strategies predicting has a long history. Deep learning techniques include analyses predictions that can assist scientists in discovering unknown patterns data. In this project, application noise elimination such as Wavelet transform Kalman filter combination deep methods were discussed time series. The results show employing filter, have considerable effect on performance LSTM neural network extracting hidden series precisely predict future actions these markets.