Research Article
[Retracted] Beat Wash-Sale Tax with Multigraph Convolutional Neural Networks Based Trading Strategy
Table 14
Summary for 20% expected return weight portfolio trading without limitation.
| 20% Expected return weight | Model | MDD | Return (%) | Counts | SR | Win rate (%) | Loss (106) | Profit (106) | Net volume (106) |
| Baseline | 0.35 | 45.06 | 1 | 1.31 | | | 0.90 | 0.75 | Random Forest | 0.07 | 7.05 | 1398 | 0.75 | 0.33 | 0.84 | 0.14 | −0.18 | XGBoost | 0.07 | 2.32 | 1422 | 0.2479 | 0.33 | 0.77 | 0.05 | −0.22 | GRU | 0.06 | 5.02 | 1187 | 0.58 | 0.33 | 0.71 | 0.10 | −0.16 | LSTM | 0.06 | 1.00 | 680 | 0.14 | 0.29 | 0.29 | 0.02 | −0.06 | Multi-GCN-GRU | 0.03 | 66.23 | 1097 | 7.50 | 0.43 | 0.07 | 1.32 | 0.84 | Multi-GCN-LSTM | 0.03 | 65.95 | 960 | 9.09 | 0.45 | 0.49 | 1.32 | 0.69 |
|
|