Stocks prediction using LSTM Recurrent Neural Network and Keras
Stocks prediction using LSTM Recurrent Neural Network and Keras The price of Tesla Stock is completely speculative (based on Guess work). If you are interested in stocks, it is very important that you know when to buy and when to sell stocks. Even though stock prediction prices are highly volatile and unpredictable , Machine learning can help in find fluctuation of prices in future by training the machine with the past data. After downloading the data it is very important and recommendable to plot the data so that you can know its behavior in the past and can predict some pattern. Long Short Term Memory are extremely powerful time series models. It allows long term and short term data modelling. Let us discuss the different components of it in details as below 1.) Cell State: Short term and Long term memory are stored here. 2.) Hidden State: Hidden State can be used to retrieve short term and long term memory. 3..) Input data: It decides how much information flow into the cell state. 4.) Forget data: How much information from current input and previous cell state flows into the current cell state. 5.) Output Gate: Decided how much data flows into the hidden state from the current state. Please watch the video and see the graph at the end. Hope this description is some value to you. https://www.youtube.com/watch?v=8aHbjIPAvZc&feature=youtu.be