Observability of information in databases - New spins in data warehousing for credit risk management

In this paper the observability of information in modem databases is investigated. Observable information is the one that is explicitly stored in a database. Unobservable information is information hidden in various coding schemes, transaction streams or free-text-description fields. Nowadays credit risk management tends to employ cutting edge technologies and approaches from the fields of statistics and machine learning for achieving their goals. Often it is forgotten that machine learning schemes can only use completely observable information. The issue is eventually addressed - but instead when using the data it should be addressed during the data warehouse design phase.