RLSTM: A New Framework of Stock Prediction by Using Random Noise for Overfitting Prevention

<div>Window slide. The green part at the top is the dataset, and the data of 20 days in the blue part is one time-step data, which is used to predict the data of 1 day ahead at the yellow part.</div>

Computational Intelligence and Neuroscience

fig4

Figure 4

Figure 4: RLSTM: A New Framework of Stock Prediction by Using Random Noise for Overfitting Prevention 