Steps towards a high-frequency financial decision support system to pricing options on currency futures with neural networks

In this paper, we present steps towards a model-driven financial decision support system (FDSS) to pricing options on currency futures, which can be embedded in a high-frequency trading process. Due to the difficulty of option valuation, we provide an alternative heuristic option pricing approach with neural networks. We show that the use of neural networks is not only suitable in generating accurate trading signals, but also in generating automated fast run-time trading signals for the decision taker. To achieve this, we conduct an experiment with an empirical tick data set of EUR/USD options on currency futures of four weeks. An essential advantage of our approach is the simultaneous pricing across different strike prices and parsimonious use of input variables. Nevertheless, we also have to take particular limitations into account, which give us useful hints for further research and steps.