The main goal of this thesis was to develop an automated trading system for Forex trading, which would use machine learning methods and their prediction models for deciding about trading actions. A training data set was obtained from exchange rates and values of technical indicators, which describe conditions on currency market. We estimated selected machine learning algorithms and their parameters with validation with sampling. We have prepared a set of automated trading systems with various settings and evaluated their performance on training data sets. The best nine automated trading systems were tested in live trading on real market with test trading accounts. Experimental results were rather good. Automated live trading was proved to be more difficult problem, because we implemented only one profitable automated trading system. We also presented possible improvements.