We focus on predicting the movement of the MSCI EURO index based on European Central Bank (ECB) statements. For this purpose we learn and extract fuzzy grammars from the text of the ECB statements. Based on a set of selected General Inquirer (GI) categories, the extracted fuzzy grammars are grouped around individual content categories. The frequency at which these fuzzy grammars are encountered in the text constitute input to a Fuzzy Inference System (FIS). The FIS maps these frequencies to the levels of the MSCI EURO index. Ultimately, the goal is to predict whether the MSCI EURO index will exhibit upward or downward movement based on the content of ECB statements, as quantified through the use of fuzzy grammars and GI content categories.

, , , ,
doi.org/10.1109/SOCPAR.2010.5686083, hdl.handle.net/1765/84100
2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010
Department of Econometrics

Milea, V., Sharef, N. M., Almeida, R., Kaymak, U., & Frasincar, F. (2010). Prediction of the MSCI EURO index based on fuzzy grammar fragments extracted from European Central Bank statements. Presented at the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010. doi:10.1109/SOCPAR.2010.5686083