Wirtschaft (MSB)
Refine
Year
Publication Type
- Conference Proceeding (112) (remove)
Keywords
- Process-Driven Application (5)
- BPMN (4)
- Artificial Intelligence (2)
- Logistics (2)
- 3D printing (1)
- Activ Investor (1)
- Activist Investor (1)
- Analytics (1)
- Asset Stripping (1)
- Augmented Reality (1)
Faculty
A major requirement for Credit Scoring models is of course to provide a risk prediction that is as accurate as possible. In addition, regulators demand these models to be transparent and auditable. Thus, in Credit Scoring very simple Predictive Models such as Logistic Regression or Decision Trees are still widely used and the superior predictive power of modern Machine Learning algorithms cannot be fully leveraged. A lot of potential is therefore missed, leading to higher reserves or more credit defaults. This talk presents an overview of techniques that are able to make “black box” machine learning models transparent and demonstrate how they can be applied in Credit Scoring. We use the DALEX set of tools to compare a traditional scoring approach with state of the art Machine Learning models and asses both approaches in terms of interpretability and predictive power. Results show that a comparable degree of interpretability can be achieved while machine learning techniques keep their ability to improve predictive power.
Process-Driven Applications flourish through the interaction between an executable BPMN process model, human tasks, and external software services. All these components operate on shared process data, so it is even more important to check the correct data flow. However, data flow is in most cases not explicitly defined but hidden in model elements, form declarations, and program code. This paper elaborates on data-flow anomalies acting as indicators for potential errors and how such anomalies can be uncovered despite implicit and hidden data-flow definitions. By considering an integrated view, it goes beyond other approaches which are restricted to separate data-flow analysis of either process model or source code. The main idea is to merge call graphs representing programmed services into a control-flow representation of the process model, to label the resulting graph with associated data operations, and to detect anomalies in that labeled graph using a dedicated data-flow analysis. The applicability of the solution is demonstrated by a prototype designed for the Camunda BPM platform.