Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
In designing credit rating systems under the new Basel Accord, considerable effort has been devoted to rating assignment and quantification, while the choice of the optimal bucket structure has received less attention. To fill this gap, we propose two "bucketing" strategies based on constrained optimisation, paying attention to the implications of rating buckets for loan-pricing and adverse selection phenomena. We compare them with some more naïve approaches, based on a sample of about 100,000 European companies. We also analyse the persistence of our performance measures over time, as well as the effect of large exposures being associated with low-PD obligors.