Use of machine learning in credit scoring

Determine default risks of loans and minimise losses.

"

Reduction of defaulted loans by over 90%



Determination of concrete default probabilities for each customer.

k

More flexible lending

Challenge

The Emergency money call is a mini loan of € 100 to € 199 with a term of 1 to 2 months. The most commonly used approach to evaluate creditworthiness is the SCHUFA report. The target group for the emergency money call partly already has entries at SCHUFA. Therefore, other distinguishing features in the customer groups must be identified in order to assess their current creditworthiness and thus their repayment probability.

Solution

Our algorithm takes into account different data such as the personal Credit history, Transactions or Social media activities to determine the probability of failure. This is calculated in real time in less than 60 seconds. This enables the bank to grant smaller loans to customers with a high probability of default. It also identifies customer characteristics that have a significant impact on repayment behaviour.

Result

Through the Client classification default risks can be identified and losses minimised for the bank and customers. The loan default rate was reduced by more than 90 % - and this at the same lending rate. Within just 3 months, the development costs for the Credit scoring.

Are you interested in your own use cases?

Challenge

An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.

Solution

There will be a interactive and Flexible application, including of different maps with two different views implemented.

Result

Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.

Contact our experts