publication . Bachelor thesis . 2016

Att förutsäga högfrekventa växelkurser med maskinlärning

Palikuca, Aleksandar; Seidl,, Timo;
Open Access English
  • Published: 01 Jan 2016
  • Publisher: KTH, Matematisk statistik
  • Country: Sweden
Abstract
This thesis applies a committee of Artificial Neural Networks and Support Vector Machines on high-dimensional, high-frequency EUR/USD exchange rate data in an effort to predict directional market movements on up to a 60 second prediction horizon. The study shows that combining multiple classifiers into a committee produces improved precision relative to the best individual committee members and outperforms previously reported results. A trading simulation implementing the committee classifier yields promising results and highlights the possibility of developing a profitable trading strategy based on the limit order book and historical transactions alone. Denna u...
Related Organizations
Download from

2 Support Vector Machines 5 2.1 Separable Classes . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2 Nonseparable Classes . . . . . . . . . . . . . . . . . . . . . . . 10 2.3 Extension to Nonlinear Decision Boundaries . . . . . . . . . . 13 2.4 The SMO Algorithm . . . . . . . . . . . . . . . . . . . . . . . 16

3 Artificial Neural Networks 19 3.1 Perceptron . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.2 Neural Network Structure . . . . . . . . . . . . . . . . . . . . 21 3.3 Neural Network Training . . . . . . . . . . . . . . . . . . . . . 22 3.4 Improvements . . . . . . . . . . . . . . . . . . . . . . . . . . . 26

4 Ensemble Learning 29 4.1 Nontrainable Committees . . . . . . . . . . . . . . . . . . . . 29 4.2 Trainable Committees . . . . . . . . . . . . . . . . . . . . . . 31

5 Implementation 33 5.1 Raw Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 5.2 Data Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . 34 5.3 Experiment Setup . . . . . . . . . . . . . . . . . . . . . . . . 36 5.4 Support Vector Machines . . . . . . . . . . . . . . . . . . . . 37 5.5 Artificial Neural Networks . . . . . . . . . . . . . . . . . . . . 39 5.6 Committees . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 5.7 Performance Measurement of Classifiers . . . . . . . . . . . . 42 5.8 Trading Simulation . . . . . . . . . . . . . . . . . . . . . . . . 43 6.1 Classification Performance . . . . . . . . . . . . . . . . . . . . 47 6.2 Trading Performance . . . . . . . . . . . . . . . . . . . . . . . 49 7 Discussion 53 7.1 Classification Performance . . . . . . . . . . . . . . . . . . . . 53 7.2 Trading Performance . . . . . . . . . . . . . . . . . . . . . . . 55 7.3 Future Work and Improvements . . . . . . . . . . . . . . . . . 57

[25] Shawe-Taylor, J., Christianini, N. 2004. Kernel Methods for Pattern Analysis. Cambridge University Press New York (2004)

[26] Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., and Hassabis, D.. 2016. Mastering The Game of Go with Deep Neural Networks and Tree Search. Nature, 529(7587):484-489

[27] Sokolova, M., Lapalme, G. 2009. A Systematic Analysis of Performance Measures for Classification Tasks. Elsevier: Information Processing and Management 45 (2009) 427-437 [OpenAIRE]

[28] Tanaka-Yamawaki, M. 2003. Stability of Markovian Structure Observed in High Frequency Foreign Exchange Data. Annals of the Institute of Statistical Mathematics, Volume 55, Issue 2, pp 437-446

Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue