Logo des Repositoriums

Auflistung nach Schlagwort "fairness"

1 - 4 von 4
  • Textdokument
    Fairness in Regression -- Analysing a Job Candidates Ranking System
    (INFORMATIK 2022, 2022) Markert,Karla; Ahouzi,Afrae; Debus,Pascal
    Fairness is one of the pillars of any well-functioning society. Recent law-making in the EU regulates the machine-centered approach and thus increases the necessity for certifiable fairness approaches. In this paper, we adapt previous literature on certifiable fairness in classification systems to a regression model for simplified candidates ranking. This model serves as an illustration for an application that should work fairly even if built upon a biased data set. With our synthetic dataset we are able to analyse the challenges of different fairness notions. Although the fairness training manages to improve the certifiable individual fairness, some of the encoded bias remains. We discuss the challenges we faced, including the selection of suitable parameters and the trade off between accuracy and fairness. We hope to encourage more research into fairness improvement and certification, within and beyond group and individual fairness.
  • Konferenzbeitrag
    Mitigating Biases using an Additive Grade Point Model: Towards Trustworthy Curriculum Analytics Measures
    (21. Fachtagung Bildungstechnologien (DELFI), 2023) Baucks, Frederik; Wiskott, Laurenz
    Curriculum Analytics (CA) tries to improve degree program quality and learning experience by studying curriculum structure and student data. In particular, descriptive data measures (e.g., correlation-based curriculum graphs) are essential to monitor whether the learning process proceeds as intended. Therefore, identifying confounders and resulting biases and mitigating them should be critical to ensure reliable and fair results. Still, CA approaches often use raw student data without considering the influence of possible confounders such as student performance, course difficulty, workload, and time, which can lead to biased results. In this paper, we use an additive grade model to estimate these confounders and verify the validity and reliability of the estimates. Further, we mitigate the estimated confounders and investigate their impact on the CA measures course-to-course correlation and order benefit. Using data from 574 Computer Science Bachelor students, we show that these measures are significantly confounded and mislead to biased interpretations.
  • Textdokument
    PhD Proposal
    (EMISA 2024, 2024) Andreswari, Rachmadita
    Process mining techniques provide operational insights into work processes in various types of organizations. These processes handle sensitive data of customers, patients, students, or citizens and their results impact the lives and careers of these affected persons. So far, much of process mining research has focused on classical dimensions of performance such a cycle time or operational cost. What is missing is a primal consideration of ethical concerns such as fairness. Fairness is a recently researched concept in machine learning, which requires a deeper integration into process mining algorithms. This research addresses this requirement. To this end, it aims to analyze fairness concerns in process mining, to develop new process mining algorithms that integrate fairness concerns, and to evaluate them for their effectiveness. Methodologically, our research will build on guidelines for design science and algorithm engineering research. In this way, we will combine engineering research with empirical evaluations.
  • Konferenzbeitrag
    RAPP: A Responsible Academic Performance Prediction Tool for Decision-Making in Educational Institutes
    (BTW 2023, 2023) Duong, Manh Khoi; Dunkelau, Jannik; Cordova, José Andrés; Conrad, Stefan
    Due to the increasing importance of educational data mining for the early intervention of at-risk students and the growth of performance data collected in educational institutes, it becomes natural to employ machine learning models to predict student's performances based off prior data. Although machine learning pipelines are often similar, developing one for a specific target prediction of academic success can become a daunting task. In this work, we present a graphical user interface which implements a customisable machine learning pipeline which allows the training and evaluation of machine learning models for different definitions of academic success, \eg, collected credits, average grade, number of passed exams, etc. The evaluation is exported in PDF format after finishing training. As this tool serves as a decision support system for socially responsible AI systems, fairness notions were included in the evaluation to detect potential discrimination in the data and prediction space.