Search, Identify, Predict: Modern methods for Credit Bureaus[go to overview]
The business model of credit bureaus is to collect and provide relevant information for assessing creditors’ risks when interacting with consumers or companies. Central tasks in managing such information are to search and identify entities for which a credit report is requested and to predict and explain the future behaviour of these entities. These tasks are commonly implemented using established and approved methods in the fields of information retrieval, data analytics and machine learning. However, modern methods which have demonstrated good performance in research and other industrial applications can be seen as challengers to the established approaches. In this talk I will give three examples of recent work in adapting and developing new methods for the needs of a credit bureau.
23.06.16 - 10:15