Research Article
A Financial Distress Prediction Model Based on Sparse Algorithm and Support Vector Machine
Table 5
Classification results of sparse principal component SVM.
| Dataset I | | Accuracy | Precision | Recall | F1 |
| OF-SVM | 72.22 | 80.77 | 58.33 | 67.74 | PCA-SVM | 75.00 | 78.13 | 72.50 | 76.32 | LDA-KNN | 55.56 | 54.55 | 66.67 | 60.00 | KPCA-SVM | 48.61 | 49.15 | 80.56 | 61.05 | KDA-KNN | 58.33 | 57.89 | 61.11 | 59.46 | SPCA-SVM | 68.06 | 72.41 | 58.33 | 64.62 | GSPCA-SVM | 81.94 | 81.08 | 83.33 | 82.19 |
| Dataset II | ā | Accuracy | Precision | Recall | F1 |
| OF-SVM | 76.27 | 94.29 | 55.93 | 70.21 | PCA-SVM | 77.96 | 94.59 | 59.32 | 72.92 | LDA-KNN | 55.08 | 55.77 | 49.15 | 52.25 | KPCA-SVM | 48.30 | 49.00 | 83.05 | 61.64 | KDA-KNN | 55.93 | 56.14 | 54.24 | 55.17 | SPCA-SVM | 62.71 | 75.86 | 37.29 | 50.00 | GSPCA-SVM | 79.66 | 92.68 | 64.41 | 76.00 |
|
|