Data pipelines for educational data mining in distance education

Abstract

New challenges in education demand effective solutions. Although Learning Analytics (LA), Educational Data Mining (EDM) and the use of Big Data are often presented as a panacea, there is a lot of ground to be covered in order for the EDM to answer the real questions of educators. An important step toward this goal is to implement holistic solutions that allow educational stakeholders to engage in the core of the EDM processes. The effectiveness of such an attempt relies on (a) having access to data arranged in an organized and meaningful way and (b) setting a sequence of processes that are flexible and reusable. Therefore, a data pipeline that imports data from a specially developed data warehouse is designed and created. Additionally, it is tested in real-life data, and results are discussed. © 2023 Informa UK Limited, trading as Taylor & Francis Group.