ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

A machine learning-based automatic currency trading system

Anže Brvar (2012) A machine learning-based automatic currency trading system. EngD thesis.

Download (1726Kb)


    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.

    Item Type: Thesis (EngD thesis)
    Keywords: foreign exchange, automated trading, machine learning, time series, foreign exchange rates movement prediction
    Number of Pages: 62
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    prof. dr. Blaž Zupan106Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=00009482324)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 1816
    Date Deposited: 19 Sep 2012 15:52
    Last Modified: 05 Nov 2012 09:17
    URI: http://eprints.fri.uni-lj.si/id/eprint/1816

    Actions (login required)

    View Item