Table 2

Results of the VSL models on test sets

Number of firmsInput sequence lengthAccuracy95% C.I.ROC-AUC
110kall lengths0.835[0.829, 0.832]0.912
55k6-7-8-90.850[0.828, 0.842]0.927
43k3-4-50.834[0.816, 0.828]0.908
54k3-5-7-90.836[0.812, 0.827]0.910

Note(s): Each model has been trained and tested by using the number of firms in the first column. The table reports the accuracy of the best model (over cross-validation) on the bankruptcy binary classification, followed by the confidence interval of accuracy over the results of cross validation and the ROC-AUC score of the best performing model

Source(s): Table created by the authors

or Create an Account

Close Modal
Close Modal