An online learning algorithm for technical trading

Simple item page
dc.contributor.advisorGebbie, Tim
dc.contributor.authorMurphy, Nicholas John
dc.date.accessioned2020-02-12T13:03:35Z
dc.date.available2020-02-12T13:03:35Z
dc.date.issued2019
dc.date.updated2020-02-12T12:15:09Z
dc.description.abstractWe use an adversarial expert based online learning algorithm to learn the optimal parameters required to maximise wealth trading zero-cost portfolio strategies. The learning algorithm is used to determine the relative population dynamics of technical trading strategies that can survive historical back-testing as well as form an overall aggregated portfolio trading strategy from the set of underlying trading strategies implemented on daily and intraday Johannesburg Stock Exchange data. The resulting population time-series are investigated using unsupervised learning for dimensionality reduction and visualisation. A key contribution is that the overall aggregated trading strategies are tested for statistical arbitrage using a novel hypothesis test proposed by Jarrow et al. [31] on both daily sampled and intraday time-scales. The (low frequency) daily sampled strategies fail the arbitrage tests after costs, while the (high frequency) intraday sampled strategies are not falsified as statistical arbitrages after costs. The estimates of trading strategy success, cost of trading and slippage are considered along with an offline benchmark portfolio algorithm for performance comparison. In addition, the algorithms generalisation error is analysed by recovering a probability of back-test overfitting estimate using a nonparametric procedure introduced by Bailey et al. [19]. The work aims to explore and better understand the interplay between different technical trading strategies from a data-informed perspective.
dc.identifier.apacitationMurphy, N. J. (2019). <i>An online learning algorithm for technical trading</i>. (). ,Faculty of Science ,Department of Statistical Sciences. Retrieved from http://hdl.handle.net/11427/31048en_ZA
dc.identifier.chicagocitationMurphy, Nicholas John. <i>"An online learning algorithm for technical trading."</i> ., ,Faculty of Science ,Department of Statistical Sciences, 2019. http://hdl.handle.net/11427/31048en_ZA
dc.identifier.citationMurphy, N. 2019. An online learning algorithm for technical trading.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Murphy, Nicholas John AB - We use an adversarial expert based online learning algorithm to learn the optimal parameters required to maximise wealth trading zero-cost portfolio strategies. The learning algorithm is used to determine the relative population dynamics of technical trading strategies that can survive historical back-testing as well as form an overall aggregated portfolio trading strategy from the set of underlying trading strategies implemented on daily and intraday Johannesburg Stock Exchange data. The resulting population time-series are investigated using unsupervised learning for dimensionality reduction and visualisation. A key contribution is that the overall aggregated trading strategies are tested for statistical arbitrage using a novel hypothesis test proposed by Jarrow et al. [31] on both daily sampled and intraday time-scales. The (low frequency) daily sampled strategies fail the arbitrage tests after costs, while the (high frequency) intraday sampled strategies are not falsified as statistical arbitrages after costs. The estimates of trading strategy success, cost of trading and slippage are considered along with an offline benchmark portfolio algorithm for performance comparison. In addition, the algorithms generalisation error is analysed by recovering a probability of back-test overfitting estimate using a nonparametric procedure introduced by Bailey et al. [19]. The work aims to explore and better understand the interplay between different technical trading strategies from a data-informed perspective. DA - 2019 DB - OpenUCT DP - University of Cape Town KW - online learning KW - technical analysis KW - portfolio selection KW - back-testing KW - statistical arbitrage KW - overfitting KW - Johannesburg Stock Exchange LK - https://open.uct.ac.za PY - 2019 T1 - An online learning algorithm for technical trading TI - An online learning algorithm for technical trading UR - http://hdl.handle.net/11427/31048 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/31048
dc.identifier.vancouvercitationMurphy NJ. An online learning algorithm for technical trading. []. ,Faculty of Science ,Department of Statistical Sciences, 2019 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/31048en_ZA
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Statistical Sciences
dc.publisher.facultyFaculty of Science
dc.subjectonline learning
dc.subjecttechnical analysis
dc.subjectportfolio selection
dc.subjectback-testing
dc.subjectstatistical arbitrage
dc.subjectoverfitting
dc.subjectJohannesburg Stock Exchange
dc.titleAn online learning algorithm for technical trading
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationnameMSc
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_sci_2019_murphy_nicholas_john.pdf
Size:
4.38 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Masters