Research Article
[Retracted] Beat Wash-Sale Tax with Multigraph Convolutional Neural Networks Based Trading Strategy
Table 7
Summary for 30% expected return weight portfolio trading without limitation.
| 30% Expected return weight | Model | MDD | Return (%) | Counts | SR | Win rate (%) | Loss (106) | Profit (106) | Net volume (106) |
| Baseline | 0.33 | 103.96 | 1 | 2.36 | | | 2.08 | 1.69 | Random Forest | 0.21 | 2.94 | 4893 | 0.11 | 0.52 | 2.79 | 0.06 | −0.96 | XGBoost | 0.25 | 20.73 | 4909 | 0.64 | 0.50 | 4.12 | 0.42 | −1.23 | GRU | 0.27 | 45.75 | 4905 | 1.29 | 0.51 | 5.83 | 0.91 | −1.55 | LSTM | 0.36 | 131.43 | 4900 | 2.43 | 0.52 | 9.68 | 2.63 | −1.89 | Multi-GCN-GRU | 0.15 | 1335.75 | 4903 | 8.57 | 0.56 | 19.80 | 26.72 | 9.54 | Multi-GCN-LSTM | 0.14 | 877.42 | 4894 | 8.69 | 0.56 | 13.74 | 17.55 | 6.01 |
|
|