Page tree
Skip to end of metadata
Go to start of metadata

The application monitors the loans for which contracts already exist. Not only are customers and contract data taken into account, but macro- and microeconomic factors that naturally influence credit management are also considered.

With the Machine Learning approach, a performance database is created, which receives the defaults, but also the loans that have not defaulted. This history is supplemented by micro- and macroeconomic boundary parameters, which are of course often the cause of default. This means that customer and contract data are placed in an overall economic context. The performance database created in this way, which was built up with deep learning, is then used as the basis for the early warning system.

The classic approach often only works with overdue payment dates (DPD). Then, unfortunately, it is often too late to change the contract, as the loan is usually already in default. At this point, the Machine Learning approach analyses the possible influences much more extensively and could alert us before a payment date becomes overdue.

The EWS app initiates a workflow when certain events occur. The events could also be the variance of the ECL, for example. The workflow actions could also be linked to contract deadlines in such a way that realistic options for action also exist.

  • No labels