Managing credit risk is one of main tasks banks encounter. It ensures business stability and presents opportunity of gaining key advantage in banking system. The focus of the master thesis is on describing the process of modelling of loss given default of housing loans. Actual solution which was built using historical data of debt collection is presented. Afterwards, the potential improvements of assessing severity of loss are introduced. Improvements consist of introducing macroeconomic factors into the model and using of machine learning methods. All the machine learning techniques, which were used for modelling, are assessed by performing quality measures. Lastly, construction of provisioning process is introduced.
|
