Penalty function in SVM classifiers applied to automated trading strategies
Kamil Piotr Żbikowski
Abstract
This thesis is dedicated to the problem of machine learning algorithms applications to the area of financial time series prediction.A new formula for constructing a penalty function that varies over time was proposed. It was used then to create an upgraded Support Vector Machine classifier. The idea of coupling penalty function and the underlying times series is motivated by the specific characteristics of financial time series. Its distribution, expected value and variance change over time. These properties directly cause difficulties in static analysis of classifications errors. Much more robust techniques should be applied.
Analysis of such data requires a dedicated computational system that would allow to adequately test the proposed classifier with the use of walk forward analysis method. Such a system was developed for the purpose of verification of the hypothesis presented in the presented thesis.
Experiments that were conducted showed that the results of short-term trends predictions with the use of proposed penalty function are better than with the use of plain penalty function . The statistical significance of the results was verified. The penalty function was then used for the purpose of constructing trading strategy. The data used for the experiments consisted of US stock and bitcoin quotations. Experiments show significant improvement in terms of the annual rate of return and the risk measured by the maximal drawdown over the test period.
- Record ID
- WUTf9d7ed681a43410bb36dc427980ef551
- Diploma type
- Doctor of Philosophy
- Author
- Title in Polish
- Konstrukcja funkcji kary dla klasyfikatorów SVM w automatycznych strategiach inwestycyjnych
- Title in English
- Penalty function in SVM classifiers applied to automated trading strategies
- Language
- (pl) Polish
- Certifying Unit
- Faculty of Electronics and Information Technology (FEIT)
- Discipline
- information science / (technology domain) / (technological sciences)
- Status
- Finished
- Start date
- 23-09-2014
- Defense Date
- 12-06-2017
- Title date
- 27-06-2017
- Supervisor
- External reviewers
- Pages
- 128
- Keywords in English
- support vector machine, penalty function, time series, investment strategies
- Abstract in English
- This thesis is dedicated to the problem of machine learning algorithms applications to the area of financial time series prediction.
A new formula for constructing a penalty function that varies over time was proposed. It was used then to create an upgraded Support Vector Machine classifier. The idea of coupling penalty function and the underlying times series is motivated by the specific characteristics of financial time series. Its distribution, expected value and variance change over time. These properties directly cause difficulties in static analysis of classifications errors. Much more robust techniques should be applied.
Analysis of such data requires a dedicated computational system that would allow to adequately test the proposed classifier with the use of walk forward analysis method. Such a system was developed for the purpose of verification of the hypothesis presented in the presented thesis.
Experiments that were conducted showed that the results of short-term trends predictions with the use of proposed penalty function are better than with the use of plain penalty function . The statistical significance of the results was verified. The penalty function was then used for the purpose of constructing trading strategy. The data used for the experiments consisted of US stock and bitcoin quotations. Experiments show significant improvement in terms of the annual rate of return and the risk measured by the maximal drawdown over the test period.
- PKT classification
- 4100
- KBN classification
- 28 Informatyka
- EU classification
- 80-30
- Thesis file
-
- File: 1
- Konstrukcja funkcji kary dla klasyfikatorów SVM w automatycznych strategiach inwestycyjnych, File Żbikowski_doktorat.pdf / 1 MB
- Żbikowski_doktorat.pdf
- publication date: 19-01-2017
- Konstrukcja funkcji kary dla klasyfikatorów SVM w automatycznych strategiach inwestycyjnych, File Żbikowski_doktorat.pdf / 1 MB
-
- Reviews
-
- File: 1
- Recenzja pracy Kamila Zbikowskiego wykonana przez prof. dr hab. inż. Jacka Koronackiego, File Żbikowski_recenzja_Koronacki.pdf / 3 MB
- Recenzja pracy Kamila Zbikowskiego wykonana przez prof. dr hab. inż. Jacka Koronackiego
- publication date: 13-06-2017
- of 10-04-2017
3 MB - Recenzja pracy Kamila Zbikowskiego wykonana przez prof. dr hab. inż. Jacka Koronackiego, File Żbikowski_recenzja_Koronacki.pdf / 3 MB
-
- File: 2
- Recenzja pracy Kamila Żbikowskiego wykonana przez prof. dr hab. inż. Andrzeja Skowrona
- of 10-05-2017
2 MB
-
- Other files
-
- File: 1
- Konstrukcja funkcji kary dla klasyfikatorów SVM w automatycznych strategiach inwestycyjnych, File Żbikowski_abstract.pdf / 171 KB
- Żbikowski_abstract.pdf
- publication date: 19-01-2017
- Konstrukcja funkcji kary dla klasyfikatorów SVM w automatycznych strategiach inwestycyjnych, File Żbikowski_abstract.pdf / 171 KB
-
- File: 2
- Konstrukcja funkcji kary dla klasyfikatorów SVM w automatycznych strategiach inwestycyjnych, File Żbikowski_streszczenie.pdf / 176 KB
- Żbikowski_streszczenie.pdf
- publication date: 19-01-2017
- Konstrukcja funkcji kary dla klasyfikatorów SVM w automatycznych strategiach inwestycyjnych, File Żbikowski_streszczenie.pdf / 176 KB
-
- Uniform Resource Identifier
- https://repo.pw.edu.pl/info/phd/WUTf9d7ed681a43410bb36dc427980ef551/
- URN
urn:pw-repo:WUTf9d7ed681a43410bb36dc427980ef551