Open Access
Table 3.
Number statistics for the training of each model.
| Classification set-up | Dataset | Mergers | Non-mergers | Pre-mergers | Post-mergers | Total |
|---|---|---|---|---|---|---|
| Two-stage step 1 | Training | 147 672 | 134 763 | – | – | 282 435 (81%) |
| Validation | 16 911 | 14 911 | – | – | 31 902 (9%) | |
| Test | 18 942 | 16 854 | – | – | 35 796 (10%) | |
| Two-stage step 2 | Training | – | – | 186 822 | 184 728 | 371 550 (80%) |
| Validation | – | – | 21 570 | 20 883 | 42 453 (9%) | |
| Test | – | – | 24 096 | 23 472 | 47 568 (10%) | |
| One-stage | Training | – | 134 763 | 134 763 | 134 763 | 404 289 (81%) |
| Validation | – | 14 991 | 14 991 | 14 991 | 44 973 (9%) | |
| Test | – | 16 854 | 16 854 | 16 854 | 50 562 (10%) | |
Notes. Percentages are shown in brackets.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.