Protecting Student Data in ML Pipelines: An Overview of Privacy-Preserving ML

Schleiss, Johannes; Günther, Kolja; Stober, Sebastian

doi:10.1007/978-3-031-11647-6_109

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A data pipeline itself is a series of data processing steps that begins with extracting raw data sets, processing the information, and managing that data in a systematic way, and then generating outputs at the end (Skiena, 2017). In education, data pipelines are utilized in order to develop early warning systems, predict student performance, and in data modeling for educational stakeholders (Ansari et al, 2017: Bertolini et al, 2021Bertolini et al, 2022;Schleiss et al, 2022). As of the time of this paper, to the best of the authors' knowledge, no publicly reported project has focused on the development of a comprehensive psychometric data pipeline for large-scale educational assessments.…”

Section: Introductionmentioning

confidence: 99%

A data pipeline for e-large-scale assessments: Better automation, quality assurance, and efficiency

SCHWARZ,

BULUT,

ANİFOWOSE

2023

International Journal of Assessment Tools in Education

View full text Add to dashboard Cite

The increasing volume of large-scale assessment data poses a challenge for testing organizations to manage data and conduct psychometric analysis efficiently. Traditional psychometric software presents barriers, such as a lack of functionality for managing data and conducting various standard psychometric analyses efficiently. These challenges have resulted in high costs to achieve the desired research and analysis outcomes. To address these challenges, we have designed and implemented a modernized data pipeline that allows psychometricians and statisticians to efficiently manage the data, conduct psychometric analysis, generate technical reports, and perform quality assurance to validate the required outputs. This modernized pipeline has proven to scale with large databases, decrease human error by reducing manual processes, efficiently make complex workloads repeatable, ensure high quality of the outputs, and reduce overall costs of psychometric analysis of large-scale assessment data. This paper aims to provide information to support the modernization of the current psychometric analysis practices. We shared details on the workflow design and functionalities of our modernized data pipeline, which provide a universal interface to large-scale assessments. The methods for developing non-technical and user-friendly interfaces will also be discussed.

show abstract