Table A4.

Predictive performance by temporal period under balanced sampling

Train yearTest yearAUCPrecisionRecallF1-Score
201820190.9720.8990.6250.716
201920200.9680.9330.6220.723
202020210.9570.8960.5310.640
202120220.9600.9190.5020.636
Note(s):

Values represent averages across 12 CPV categories for each temporal period. The narrow range in AUC (0.957–0.972) and precision (0.896–0.933) demonstrates temporal stability of structural prediction patterns, while modest variation in recall reflects either changing procurement dynamics or increased relationship complexity in later years

or Create an Account

Close subscription notice
Close access options