Stock Price Prediction Based on Natural Language Processing¹

Figure 2

Basic structure of LSTM. In this context, C_t represents the cell state value at time (t); X_t represents the input value at time (t); H_t represents the cell output value at time (t) σ(·); and tanh (·) represent the activation function of updated information; (W) and (b) represent the weight matrix and bias of each gate control, respectively.