Dataset Information

Facing the Challenges of Developing Fair Risk Scoring Models

ABSTRACT: Algorithmic scoring methods are widely used in the finance industry for several decades in order to prevent risk and to automate and optimize decisions. Regulatory requirements as given by the Basel Committee on Banking Supervision (BCBS) or the EU data protection regulations have led to an increasing interest and research activity on understanding black box machine learning models by means of explainable machine learning. Even though this is a step into a right direction, such methods are not able to guarantee for a fair scoring as machine learning models are not necessarily unbiased and may discriminate with respect to certain subpopulations such as a particular race, gender, or sexual orientation—even if the variable itself is not used for modeling. This is also true for white box methods like logistic regression. In this study, a framework is presented that allows analyzing and developing models with regard to fairness. The proposed methodology is based on techniques of causal inference and some of the methods can be linked to methods from explainable machine learning. A definition of counterfactual fairness is given together with an algorithm that results in a fair scoring model. The concepts are illustrated by means of a transparent simulation and a popular real-world example, the German Credit data using traditional scorecard models based on logistic regression and weight of evidence variable pre-transform. In contrast to previous studies in the field for our study, a corrected version of the data is presented and used. With the help of the simulation, the trade-off between fairness and predictive accuracy is analyzed. The results indicate that it is possible to remove unfairness without a strong performance decrease unless the correlation of the discriminative attributes on the other predictor variables in the model is not too strong. In addition, the challenge in explaining the resulting scoring model and the associated fairness implications to users is discussed.

SUBMITTER: Szepannek G

PROVIDER: S-EPMC8552888 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Considering the real-world experiences of those with cognitive impairments is important in building a positive community for older people. Community-based participatory research is an important methodology for investigators focused on improving community health. The aim of this study was to 1) investigate factors associated with the continuation of community dwelling among high-risk older people and 2) to create a model of an inclusive community space for older people in the largest housing complex district in Tokyo. METHODS:From 198 residents who completed all three steps (mail, face-to-face, and home-visit) of a previous large-scale epidemiological survey, we identified 66 residents who were at high-risk of moving out of the community. These participants underwent 6 months of regular assessments by experienced researchers to identify the factors associated with continuing to live in the community. We also employed a community action approach to develop a community space for residents in the study district where more than two researchers who were medical professionals served as staff. The services offered by the space were continuously improved according to user feedback. The function of this center was evaluated during interdisciplinary research meetings. RESULTS:After 6 months, among the 66 high-risk residents, 49 people were living in the community and 12 people had moved out of the community. Those who could not continue to live in the community had greater unmet needs in terms of social support, especially daily living support and housing support. In addition, their families perceived a heavier burden of care. Interestingly, dementia diagnosis via the DSM-5, clinical dementia rating, physical health, mental health, and long-term care usage did not predict the outcome. Through discussions with guests, we equipped the space with various services such as coordination of community care and networking with existing organizations. CONCLUSIONS:Merely providing healthcare and long-term care might not be sufficient to support community living in people with cognitive impairments. Daily living support and housing support should be provided in the context of a broad health services package. For this purpose, creating a comfortable community space for residents and community workers is essential.

Dataset Information

Facing the Challenges of Developing Fair Risk Scoring Models

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets