|
|
Einrichtungen >> Fakultät Sozial- und Wirtschaftswissenschaften >> Bereich Statistik und Wirtschaftsmathematik >> Lehrstuhl für Statistik und Ökonometrie in den Sozial- und Wirtschaftswissenschaften >>
|
Machine Learning for Digitalization and Automatization in Official Statistics? Methodological Perspectives and Challenges- Dozentinnen/Dozenten
- LMU München, Dr. Florian Meinfelder
- Angaben
- Seminar
Rein Online
To apply for participation please write an email to support.statmath@uni-bamberg.de before October 19th. Please use the subject "[EMOS Seminar: Student from Bamberg]" and send us your name, your email address at the University of Bamberg and briefly explain your prior knowledge in official statistic and machine learning. To foster discussions and intensive exchange among the students the number of participants is limited.
Ort: Online-Meeting; Bemerkung zu Zeit und Ort: The seminar will start with a first meeting via Zoom on an evening at the end of October/early November (exact dates will be determined in agreement with the participants). There, the different seminar topics are briefly introduced and allocated among the participants. The core part of the seminar with the presentations and discussions will be on some Friday afternoons/Saturdays in late January and early February next year. Regular participation in all meetings and active engagements in the seminar discussions are expected.
- Voraussetzungen / Organisatorisches
- Florian Dumpert (German Federal Statistical Office, Artificial Intelligence and Big Data Unit)
Thomas Augustin (Foundations of Statistics and Their Applications, LMU Munich)
- Inhalt
- The seminar discusses methodological aspects of recent developments in machine learning (ML) for digitalization and automatization in official statistics. On the one hand, ML promises excellent opportunities for innovation along the whole statistical production process, from data collection and editing to powerful prediction and even dissemination. On the other hand, it is still an open question to what extent one can reconcile the strongly prediction-oriented ML methods with the quality requirements of official statistics, like transparency, neutrality, and objectivity.
Eligible for the seminar are Master’s students with prior background knowledge in both ML and official statistics.
Students can obtain 9 ECTS credits for a seminar presentation and a term paper or 3 ECTS credits for a shorter presentation.
- Englischsprachige Informationen:
- Title:
- Machine Learning for Digitalization and Automatization in Official Statistics? Methodological Perspectives and Challenges
- Credits: 9
Hinweis für Web-Redakteure:
Wenn Sie auf Ihren Webseiten einen Link zu dieser Lehrveranstaltung setzen möchten, verwenden Sie bitte einen der folgenden Links:Link zur eigenständigen Verwendung Link zur Verwendung in Typo3
|
 |
|
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|