Research Article
[Retracted] Beat Wash-Sale Tax with Multigraph Convolutional Neural Networks Based Trading Strategy
Table 15
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 | 0.11 | 36.11 | 1398 | 2.23 | 0.33 | 1.50 | 0.72 | −0.06 | XGBoost | 0.11 | 39.48 | 1422 | 2.42 | 0.33 | 1.47 | 0.79 | −0.01 | GRU | 0.15 | 15.54 | 1187 | 1.08 | 0.33 | 1.78 | 0.31 | −0.43 | LSTM | 0.06 | 28.50 | 680 | 2.87 | 0.29 | 1.18 | 0.57 | −0.04 | Multi-GCN-GRU | 0.03 | 104.24 | 1097 | 9.02 | 0.43 | 0.81 | 2.08 | 1.05 | Multi-GCN-LSTM | 0.06 | 142.03 | 960 | 8.91 | 0.45 | 1.05 | 2.84 | 1.44 |
|
|