Financial Data Analytics in Python

Prof. Dr. Fabian Woebbeking
Assistant Professor of Financial Economics

IWH - Leibniz Institute for Economic Research
MLU - Martin Luther University Halle-Wittenberg

[email protected]

Birte Winter
PhD Candidate, Teaching Assistant (TA)

IWH - Leibniz Institute for Economic Research

[email protected]

Course Description

This course is designed to provide students with a hands-on understanding of the use of data science techniques in the field of finance. Students will learn how to collect, clean, and analyze financial data using Python, SQL and other tools. Topics will include financial data visualization, time series analysis and statistical modeling. Students will work on real-world projects to apply their knowledge to financial data.

Prerequisites

• Strong interest and pre-knowledge in financial economics
• Basic knowledge of programming (preferably Python) and statistics
• All the software used during this course are open-source and/or free, this includes:
  • Python (Anaconda distribution): https://www.anaconda.com/products/distribution
  • Git: https://git-scm.com/
  • GitHub: https://skills.github.com/

Studip (course schedule)

The course shedule is available at: https://studip.uni-halle.de/dispatch.php/course/details?sem_id=ceee7624465e9d8fa7fdbff72265df10

Materials

The course is hosted as a Git repository on GitHub: https://github.com/cafawo/FinancialDataAnalytics

FinancialDataAnalytics/
├── cases/  # Case description and supplements
│   └── ...  
├── figures/  # Figures used in slides.ipynb
│   └── ...  
├── homework/  # Homework assignments and solutions
│   └── ...  
├── src/  # Python scripts (.py)
│   └── ...  
├── README.md  # Syllabus
├── slides.ipynb  # MAIN source of information for this class
├── slides.html   # Static version of the script
└── ...  # TBA

As a backup, instead of opening .ipynb files locally, you can open the slides

• using Google's Colab HERE.
• or as a static (offline) html version HERE.

This course is predominantly hands on and draws from several subject areas, such as financial economics, data science or textual analysis. As such, there exists no single text book recommendation. Relevant 'reading' material is linked in the script. That being said, resources include but are not limited to:

• "Python for Finance" (Yves Hilpisch)
• "Data Analysis for Business, Economics, and Policy" (Gabor Bekes, Gabor Kezdi)
• "Applied Text Analysis with Python" (Benjamin Bengfort, Rebecca Bilbro, Tony Ojeda)
• "The big short" (A. McKay)
• "Margin Call" (J. C. Chandor)
• https://stackoverflow.com/
• https://docs.python.org/3/tutorial/index.html

Grading Policy

The grading policy is discussed in detail during the first lecture.

• Homework assignments: 20%
• Case studies: 50%
• Presentation: 30%
• Bonus points: + 15%
  • Participation in GitHub discussions: https://github.com/cafawo/FinancialDataAnalytics/discussions
  • Bug bounty (pull requests): https://github.com/cafawo/FinancialDataAnalytics/pulls

How to submit your work

All students are requested to commit and push their homework, cases and presentation material to one GitHub repository. We will discuss this during the first lecture, also see /homework/01_setup.ipynb. In order to submit your hard work, you are requested to add GitHub user: 'birte0' to your repository before the last lecture(!), see information on how to invite collaborators HERE. We will notify you once your repository has been successfully registered.

Deadlines

• Homework assignments have to be commited before the subsequent lecture
• Case submission deadlines will be announced with the case description

The deadlines for all deliverables are tracked through their commit timestamp. As such, it does not matter at what point in time during the lecture you register your GitHub repository (see previous section). Should you be interested in the timestamp for a specific commit, try this:

git show -s <commit>

Lectures

Lecture 1: Introduction (slides.ipynb)

• Discussion of grading scheme
• Setting up the tech
  • Git and GitHub
  • Necessary Python libraries (Anaconda distribution)
• Introduction to the Python programming language

Lecture 2: Python basics (slides.ipynb)

• Data types and structures
• Packages and modules
• Complex data structures
• Plotting

Lecture 3, 4: Stochastics and numerical methods (slides_pt2.ipynb)

• Random numbers
• Probability distributions
• Cholesky decomposition
• Numerical integration
• Numerical optimization
• Stochastic processes
• Monte Carlo simulation
• Valuation
• Risk measures

...

Disclaimer:

This syllabus is a general plan for the course; deviations announced to the class by the instructor may be necessary.