companies display only small improvements in the accuracy ratio
(2.9 and 3.9 percentage points, respectively). Public sector companies’
credit quality typically depends on public owner’s willingness
to cover losses, which makes their default behavior more idiosyncratic.
Rental companies pursue a very specific business model
(e.g., long-term leasing by car rental companies). The five industries
that are below the diagonal are relatively small and/or specialized
(code 5: fishing; code 24: chemicals; code 73: R&D; code
90: sewage and waste disposal; code 95: private households),
and they exhibit already a relatively high baseline AR. In sum, we
show that the influence of business credit information on the default
prediction accuracy varies substantially across industries.
This finding is novel since previous studies have either focused
on a cross-country perspective or samples of firms from single
industries.