Search

Machine learning and deep learning algorithms produce very different results with different examples of their hyperparameters. Algorithm parameters require optimization because they are not specific to all problems. This paper used Long Short-Term Memory (LSTM) and eight different hyperparameters (go-backward, epoch, batch size, dropout, activation function, optimizer, learning rate, and the number of layers) to examine daily and hourly Bitcoin datasets. The effects of each parameter on the daily dataset on the results were evaluated and explained. These parameters were examined with the hparam properties of Tensorboard. As a result, it was seen that examining all combinations of parameters with hparam produced the best test Mean Square Error (MSE) values with hourly dataset 0.000043633 and daily dataset 0.00061806. Both datasets produced better results with the tanh activation function. Finally, when the results are interpreted, the daily dataset produces better results with a small learning rate and dropout values. In contrast, the hourly dataset produces better results with a large learning rate and dropout values. [ABSTRACT FROM AUTHOR]