Måns Tillman from Royal Institute of Technology (KTH) has published a thesis in collaboration with Scila. The title of the thesis is “On-Line Market Microstructure Prediction Using Hidden Markov Models”.
In this thesis, we model the dynamics of high frequency markets using non-linear hidden Markov models (HMMs). Such models feature an intuitive separation between observations and dynamics, and are therefore highly convenient tools in financial settings, where they allow a precise application of domain knowledge. HMMs can be formulated based on only a few parameters, yet their inherently dynamic nature can be used to capture well-known intra-day seasonality effects that many other models fail to explain.
Download the thesis via the following link: