Research Article
A Destination Prediction Network Based on Spatiotemporal Data for Bike-Sharing
Table 6
Results of candidate generation.
| | Methods | Recall | Mean |
| | User-Destination Count (UD) | 60.89% | 7.76 | | User-Origin Count (UO) | 84.51% | 63.38 | | Origin-Destination Count (OD) | 86.13% | 68.31 |
| | Our Methods | | | | Candidate Generation Model1 (CGM1) | | | | | 91.02% | 58.29 | | Candidate Generation Model2 (CGM2) | | | | | 92.81% | 97.57 | | Candidate Generation Model3 (CGM3) | | | | | 93.34 | 66.70 | | Candidate Generation Model4 (CGM4) | | | | | 96.57% | 91.58 |
|
|
