Currently, my research focuses on machine learning, causal inference and time series analysis for multi-agent and economic decision making problems.
- Here's my CV as PDF, if you want to get a quick overview over my qualifications and experience.
- If you are interested in my research, have a look at my publications, slides, blog and software.
Implementing time series multi-step ahead forecasts using recurrent neural networks in TensorFlow:
Recently I started to use recursive neural networks (RNNs) in TensorFlow (TF) for time series forecasting. Specifically, I’d like to perform multistep ahead forecasts and I was wondering how to do this (1) with RNNs in general and (2) in TF in particular. Here I summarize my insights. In particular I give a short overview over some available approaches. Furthermore, I provide code on GitHub which evaluates two simple approaches on real data.
[Read more. Posted on 2018-05-26.]
Coordination via predictive assistants from a game-theoretic view:
How can predictive computational assistants - similar to Google’s “Popular Times” - help for coordination between humans in congested facilities? We analyze this problem using causal, time series and game theoretic models as well as real experiments in our campus cafeteria. Check out our preprint “Coordination via predictive assistants from a game-theoretic view”!
[Posted on 2018-03-19. Updated on 2018-04-07.]
In June, I passed the final exam of my PhD. The final version of my thesis “Causal models for decision making via integrative inference” is available for download.
[Posted on 2017-08-29. Updated on 2017-10-08.]
Causal models for cloud computing:
We are investigating how causal models can help for debugging, control and economical challenges in cloud computing. Check out our preprint!
[Posted on 2016-06-03.]