Hier finden Sie von Know-Center MitarbeiterInnen verfasste wissenschaftliche Publikationen


Andrusyak Bohdan, Kugi Thomas, Kern Roman

Daily Prediction of Foreign Exchange Rates Based on the Stock Marke

Proceedings of the PEFNet 2017 conference, Jana Stávková, Mendel University Press, Brno, 2018

The stock and foreign exchange markets are the two fundamental financial markets in the world and play acrucial role in international business. This paper examines the possibility of predicting the foreign exchangemarket via machine learning techniques, taking the stock market into account. We compare prediction modelsbased on algorithms from the fields of shallow and deep learning. Our models of foreign exchange marketsbased on information from the stock market have been shown to be able to predict the future of foreignexchange markets with an accuracy of over 60%. This can be seen as an indicator of a strong link between thetwo markets. Our insights offer a chance of a better understanding guiding the future of market predictions.We found the accuracy depends on the time frame of the forecast and the algorithms used, where deeplearning tends to perform better for farther-reaching forecasts

Andrusyak Bohdan, Kern Roman, Rimel Myhailo

Detection of abusive speech for mixed sociolects of Russian and Ukrainian language

Tribun Eu, 2018

Uncontrolled use of abusive language is a problem in modern society. Development of automatic tools for detecting abusive and hate speech has been an active research topic in the past decade. However, very little research has been done on this topic for Russian and Ukrainian languages. To our best knowledge, no research considered surzhyk. We propose to use unsupervised probabilistic technique with a seed dictionary for detecting abusive comments in social media in Russian and Ukrainian languages. We demonstrate that this approach is feasible and is able to detect abusive terms that are not present in the seed dictionary
Kontakt Karriere

Hiermit erkläre ich ausdrücklich meine Einwilligung zum Einsatz und zur Speicherung von Cookies. Weiter Informationen finden sich unter Datenschutzerklärung

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.