Back to Article
Stock Closing Price and Trend Prediction with LSTM-RNN
Journal of Artificial Intelligence and Big Data
| Vol 4, Issue 1
Table 1. Performance metrics for different combinations of hyperparameters of theLSTM model. Intuitively, the number of epochs is significant in training themodel since none of the combinations feature an epoch number of 50 in the top10
| Number of Units in First Layer | Batch Size | Epochs | RMSE | MAE | MAPE |
| 641281283264641283232 | 646432323232323264 | 200200200200100200100100200 | 2.8242.8272.8322.8622.8792.8812.9212.9672.995 | 2.0432.0492.0602.1062.0992.1372.1402.1882.219 | 1.5101.5131.5231.5571.5481.5811.5771.6131.635 |