Case Study

Website: www.rsnag.ch
Sector: Banking
Location: Switzerland
Solutions: DetectX-CR

About Risk Solution Network

Risk Solution Network AG (RSN) is a subsidiary of the Swiss cantonal banks of Basel, Lucerne and St. Gallen. With the aim to be the leading outsourcing structure in credit risk management for small and medium sized Swiss financial institutions, RSN currently provides more than 30 banks a set of tools designed to measure and validate hedge credit risks (financial analysis, rating, LGD and pricing concepts).

This set of tools constitutes the common pool of data, which is the basis for the enhancement and validation of the models, as well as other tailored services (reporting, benchmarking). Furthermore, RSN offers its customers a platform where they can exchange knowledge and experiences, and which enables them a concentrated representation of interests towards external target groups and segments.

The project and the results

Step 1 - Service project: Optimisation of the rating model.

As a result of financial analyses, default data and other qualitative criteria, RSN identified a set of distinguishing key indicators (operating figures) and qualitative factors. Not only indicators for short-term risks were looked for, but also factors which lead to a positive constant company development. The correct weighting of all factors provides the nec- essary requirements for an efficient rating model not only as basis for credit approvals but also for fair risk pricing. This requires the use of highly developed and stable optimization algorithms. Prospero improved RSN’s rating processes with the DetectX-CR solution.

«Prospero’s solution has enabled us to develop an optimally separating rating function, which has proved to be very reliable not only by its appli- cation in the banks but also in the validation of the model.»

Prof. Dr. Markus Heusler, CEO
Risk Solution Network AG

The challenge in this project was to find scoring processes, which would improve the Gini coefficients or the ROC curve, abiding by several restrictions predetermined by RSN. The optimised scoring calculations constitute the basis of the rating models which are currently being used at RSN banks to rate the customers of the segment small and medium enterprises (SME).

Step 2 - Internal use of DetectX-CR by RSN

In the second phase there was a three days training for the employees from RSN. They use DetectX-CR for the creation, validation and calibration of their rating models.

The DetectX-CR Solution

With the DetectX-CR solution the Basel III requirements can be easily implemented – in a secure, consistent and law-abiding way. The users benefit from the system’s learning process that originates from creating forward-looking rating models and from validating or calibrating existing applications. The system by itself finds in this learning process error minimised rating models with maximised separation power. The user can simulate different risk strategies and optimise his credit business. The created models are based on the fewest possible attributes to guarantee an easy reasoning of the rating. All activities are tracked and may be recorded at any time.