Markus is an Energy Professional with more than ten years of experience in various roles in the European natural gas and power markets with the utilities RWE and Uniper. His focus is on the origination and pricing of structured gas products like natural gas storage capacities and flexible supply contracts. Recently he has been applying machine learning methods to forecast portfolio offtakes/imbalances and market prices.
Before switching to the energy sector, he obtained a Ph.D. in mathematics from Swansea University, UK, and thereafter researched and taught at the Technical University of Braunschweig, Germany.
In this paper, different machine learning approaches are applied to forecasting future yearly price trends in the natural gas Title Transfer Facility market in the Netherlands.
This paper introduces a three-factor model that jointly describes both natural gas forward prices and temperature forecast dynamics.