Fair, Accountable, and Transparent Decision Support

Machine learning models are commonly used for decision support. Ideally, the decisions should be impartial, unbiased, and fair. However, machine learning models are far from perfect, e.g., due to bias introduced by imperfect training data or wrong feature selection. While efforts are made and should continue to be put into developing better models, we also acknowledge that we will continue to rely on imperfect models in many applications. But what if we can provably rely on the “best” model for an individual or a group of individuals and transparently communicate the risks and weaknesses that apply?

In light of this question, we propose a system framework that optimizes the choice of model for specific subgroups of the population or even individual persons, relying on metadata sheets for data and models. At the same time, to achieve transparency, the framework captures data to explain the choices made and results of the model at different scales to different stakeholders.

Publications

  1. Lässig, N., Oppold, S., & Herschel, M. (2021). Using FALCES against bias in automated decisions by integrating fairness in dynamic model ensembles (to appear). In Proceedings of Database Systems for Business, Technology, and Web (BTW).
  2. Lässig, N., Oppold, S., & Herschel, M. (2021). Using FALCES against bias in automated decisions by integrating fairness in dynamic model ensembles (to appear). In Proceedings of Database Systems for Business, Technology, and Web (BTW).
  3. Oppold, S., & Herschel, M. (2020). Accountable Data Analytics Start with Accountable Data: The LiQuID Metadata Model. ER Forum, Demo and Posters 2020 Co-Located with International Conference on Conceptual Modeling (ER), 59--72. http://ceur-ws.org/Vol-2716/paper5.pdf
  4. Oppold, S., & Herschel, M. (2020). A System Framework for Personalized and Transparent Data-Driven Decisions. Proceedings of the International Conference on Advanced Information Systems Engineering (CAiSE), 153–168. https://doi.org/10.1007/978-3-030-49435-3_10
  5. Oppold, S., & Herschel, M. (2019). LuPe: A System for Personalized and Transparent Data-driven Decisions. Proceedings of the International Conference on Information and Knowledge Management (CIKM), 2905–2908. https://doi.org/10.1145/3357384.3357857
To the top of the page