In February of 2016, I finished my master's thesis at TU-Berlin.
Title: "Predicting the Development of Financial Markets by Applying Machine Learning Tools to Social Media Data"
The thesis has received a grade of 1.3 ("very good") and is available here.
While working on the thesis, I wrote the Python package "TwistML", which is available at PyPI and BitBucket. TwistML is a package that makes it easier to work with raw twitter data for machine learning tasks, like predicting changes in the stock market.
During this time I acquired a lot of experience working with Python and many different machine learning methods and tools. In particular I worked intensively with the Python packages "scikit-learn", "numpy" and "nltk".