Table 6 Comparative Experiments.
From: PMANet: a time series forecasting model for Chinese stock price prediction
Method | PMANet | Autoformer | Transformer | FEDformer | Informer | CEEMD-CNN-LSTM | LSTM | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Metrics | MSE | MAE | MSE | MAE | MSE | MAE | MSE | MAE | MSE | MAE | MSE | MAE | MSE | MAE | ||
JT | 24 | 0.412 | 0.431 | 0.532 | 0.502 | 0.396 | 0.448 | 0.734 | 0.641 | 0.593 | 0.538 | 0.579 | 0.518 | 0.697 | 0.564 | |
48 | 0.515 | 0.502 | 0.508 | 0.546 | 0.711 | 0.591 | 0.761 | 0.663 | 0.583 | 0.505 | 0.622 | 0.532 | 0.718 | 0.577 | ||
GL | 24 | 0.122 | 0.278 | 0.321 | 0.455 | 1.108 | 1.011 | 0.305 | 0.432 | 0.286 | 0.421 | 0.315 | 0.421 | 0.237 | 0.381 | |
48 | 0.124 | 0.278 | 0.192 | 0.351 | 3.874 | 1.946 | 0.327 | 0.438 | 0.315 | 0.429 | 0.284 | 0.409 | 0.284 | 0.409 | ||
THS | 24 | 0.531 | 0.498 | 0.585 | 0.538 | 1.109 | 0.804 | 2.351 | 1.193 | 0.771 | 0.667 | 0.759 | 0.664 | 0.729 | 0.645 | |
48 | 0.868 | 0.661 | 0.891 | 0.683 | 1.727 | 1.135 | 2.746 | 1.312 | 0.783 | 0.665 | 0.727 | 0.647 | 0.781 | 0.677 | ||
HR | 24 | 0.182 | 0.352 | 0.336 | 0.473 | 0.583 | 0.672 | 0.477 | 0.497 | 0.67 | 0.555 | 0.261 | 0.397 | 0.654 | 0.717 | |
48 | 0.261 | 0.423 | 0.275 | 0.431 | 0.657 | 0.694 | 0.568 | 0.506 | 0.562 | 0.549 | 0.289 | 0.411 | 0.711 | 0.768 | ||
KM | 24 | 0.265 | 0.183 | 0.347 | 0.359 | 0.413 | 0.462 | 0.313 | 0.352 | 0.178 | 0.318 | 0.585 | 0.511 | 0.716 | 0.788 | |
48 | 0.308 | 0.329 | 0.569 | 0.561 | 0.557 | 0.584 | 0.447 | 0.489 | 0.307 | 0.366 | 0.747 | 0.708 | 0.934 | 0.905 | ||
BYD | 24 | 0.175 | 0.254 | 0.228 | 0.256 | 0.284 | 0.407 | 0.271 | 0.355 | 0.194 | 0.278 | 0.711 | 0.725 | 1.246 | 1.095 | |
48 | 0.232 | 0.257 | 0.489 | 0.467 | 0.573 | 0.594 | 0.589 | 0.673 | 0.273 | 0.261 | 0.879 | 0.828 | 1.512 | 1.183 |