I am a postdoctoral researcher in machine learning at the Department of Engineering Science of the University of Oxford. Previously, I headed the Social Computing & Finance Research Group at the Chair of Information Systems at the University of Freiburg where I also obtained my Ph.D. in Information Systems. My research primarily focuses on data science methods and computational techniques for understanding human decision-making in the digital age. Current projects examine, for example, the role of social media (e.g. Twitter) in shaping public opinions regarding businesses and products. Related studies apply machine learning techniques and quantitative text analysis to a broad selection of topics, including financial markets and recommender systems. Apart from these projects, I am a passionate programmer and interested in developing novel data science methods with high business value.
A list of publications can be found here.
Further resources can be found here.
This package performs model-free reinforcement learning in R. The implementation enables the learning of an optimal policy based on sample sequences consisting of states, actions and rewards. In addition, it supplies multiple predefined reinforcement learning algorithms, such as experience replay.
ReinforcementLearning on CRAN: https://cran.r-project.org/web/packages/ReinforcementLearning/index.html
This package performs a sentiment analysis of textual contents in R. The implementation utilizes various existing dictionaries, such as Harvard IV, or finance-specific dictionaries. Furthermore, it can also create customized dictionaries. The latter uses LASSO regularization as a statistical approach to select relevant terms based on an exogenous response variable.
SentimentAnalysis on CRAN: