TY  - CHAP
A1  - Bücker, Michael
A1  - Szepannek, Gero
A1  - Biecek, Przemyslaw
A1  - Gosiewska, Alicja
A1  - Staniak, Mateusz
ED  - Crook, Jonathan
T1  - Transparency of Machine Learning Models in Credit Scoring
T2  - CRC Conference XVI Papers
N2  - 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.
Y1  - 2019
UR  - https://crc.business-school.ed.ac.uk/wp-content/uploads/sites/55/2019/07/C13-Transparency-of-Machine-Learning-Models-in-Credit-Scoring-B%C3%BCcker.pdf
SP  - 1
EP  - 1
PB  - Credit Research Center, University of Edinburgh
CY  - Edinburgh
ER  - 
TY  - CHAP
A1  - Bücker, Michael
A1  - Kayser, Franz
A1  - Mayer, Thomas
T1  - Addressing Challenges in a Dangerous World: Developing a Design Science Artifact for Advancing Open Source Intelligence (OSINT) Research
T2  - Proceedings of the 58th Hawaii International Conference on System Sciences
N2  - Open Source Intelligence (OSINT), deriving intelligence from public data, has gained scrutiny since the Russian invasion of Ukraine. Despite numerous attempts at standard definitions, research around technology-driven intelligence gathering and analysis remains ambiguous. This paper uses a Design Science Research (DSR) approach to categorize the technology-driven intelligence construct. Analyzing sixty studies via structured literature review, three domains were identified: maturity, Intelligence Cycle phase, and use case. The resulting framework, developed into a trend radar, was evaluated with expert interviews, revealing technological gaps in planning/direction and dissemination/integration phases. While intelligent support technologies were noted, practical implementation lags behind theory. The human factor remains central to OSINT. Findings suggest future research should develop applications for underserved phases and examine why proven applications are not widely adopted, considering legal, ethical, political, and social factors. This study contributes to technology-driven intelligence literature as a knowledge base, research gap identifier, and guide for further research.
Y1  - 2025
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:836-opus-186518
UR  - https://hdl.handle.net/10125/109494
SN  - 978-0-9981331-8-8
SP  - 5370
EP  - 5379
PB  - University of Hawaiʻi at Mānoa Library
ER  -