Universität Wien

040514 KU Python for Finance II (MA) (2020S)

4.00 ECTS (2.00 SWS), SPL 4 - Wirtschaftswissenschaften
Prüfungsimmanente Lehrveranstaltung

An/Abmeldung

Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first served").

Details

max. 35 Teilnehmer*innen
Sprache: Englisch

Lehrende

Termine (iCal) - nächster Termin ist mit N markiert

This course will take place via video conferencing at the originally scheduled times. Detailed announcements will be available on Moodle.

Dienstag 05.05. 13:15 - 16:30 PC-Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Untergeschoß
Dienstag 12.05. 13:15 - 16:30 PC-Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Untergeschoß
Dienstag 19.05. 13:15 - 16:30 PC-Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Untergeschoß
Dienstag 26.05. 13:15 - 16:30 PC-Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Untergeschoß
Dienstag 09.06. 13:15 - 16:30 PC-Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Untergeschoß
Dienstag 16.06. 13:15 - 16:30 PC-Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Untergeschoß
Dienstag 23.06. 13:15 - 16:30 PC-Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Untergeschoß
Dienstag 30.06. 13:15 - 16:30 PC-Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Untergeschoß

Information

Ziele, Inhalte und Methode der Lehrveranstaltung

The course enables participants to gain further experience in Python and its applications in Finance. It is expected that students have prior knowledge of Python equivalent to the contents of Python for Finance I. Participants get to know and apply methods from machine learning and natural language processing, with a focus on practical applications of these methods. Students learn to gather textual data from different internet sources, clean the data, and process the data to produce quantitative measures that might be relevant for an investment strategy. Subsequently, this data and other standard finance data sources are used to develop an investment or trading strategy based both on standard econometric data analysis and machine learning methods. Besides these specific methods, students will also gain further general knowledge with respect to Python programming and managing a programming project.

Art der Leistungskontrolle und erlaubte Hilfsmittel

The grade will be based on homework exercises that participants are expected to present in class, class participation, and a course project in which students apply the methods learnt in the course.

Mindestanforderungen und Beurteilungsmaßstab

40% homework exercises
20% class participation
40% course project

Minimum requirement for a positive grade: a total of 50%.

Prüfungsstoff

All material covered in class.

Literatur

Bird, S., Klein, E., Loper, E., Natural Language Processing with Python, 2019. https://www.nltk.org/book/

Géron, A., Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 1st (2017) or 2nd (2019) edition. O'Reilly Media.

Raschka, S., Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd (2017) or 3rd (2019) edition. Packt Publishing.
or
Raschka, S., Machine Learning mit Python und Scikit-Learn und TensorFlow : das umfassende Praxis-Handbuch für Data Science, Predictive Analytics und Deep Learning, 2. Auflage, 2018. MITP.

Zatloukal, K., ML & Investing Part 1: From Linear Regression to Ensembles of Decision Stumps, 2018. https://www.osam.com/Commentary/ml-investing-linear-regression-to-decision-stumps

Zatloukal, K., ML & Investing Part 2: Clustering, 2019. https://osam.com/pdfs/research/ML-and-Investing-Part-2-Clustering.pdf

AQR Capital Management, Can Machines "Learn" Finance? 2019. https://images.aqr.com/-/media/AQR/Documents/Alternative-Thinking/AQR-Alternative-Thinking-2Q19-Can-Machines-Learn-Finance.pdf

Zuordnung im Vorlesungsverzeichnis

Letzte Änderung: Mo 07.09.2020 15:19