AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets

dc.contributor.advisorGeorg, Co-Pierre
dc.contributor.authorNtsaluba, Kuselo Ntsika
dc.date.accessioned2020-02-20T09:42:27Z
dc.date.available2020-02-20T09:42:27Z
dc.date.issued2019
dc.date.updated2020-02-14T08:12:15Z
dc.description.abstractIn this study, a methodology is presented where a hybrid system combining an evolutionary algorithm with artificial neural networks (ANNs) is designed to make weekly directional change forecasts on the USD by inferring a prediction using closing spot rates of three currency pairs: EUR/USD, GBP/USD and CHF/USD. The forecasts made by the genetically trained ANN are compared to those made by a new variation of the simple moving average (MA) trading strategy, tailored to the methodology, as well as a random model. The same process is then repeated for the three major cryptocurrencies namely: BTC/USD, ETH/USD and XRP/USD. The overall prediction accuracy, uptrend and downtrend prediction accuracy is analyzed for all three methods within the fiat currency as well as the cryptocurrency contexts. The best models are then evaluated in terms of their ability to convert predictive accuracy to a profitable investment given an initial investment. The best model was found to be the hybrid model on the basis of overall prediction accuracy and accrued returns.
dc.identifier.apacitationNtsaluba, K. N. (2019). <i>AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets</i>. (). ,Faculty of Commerce ,African Institute of Financial Markets and Risk Management. Retrieved from http://hdl.handle.net/11427/31185en_ZA
dc.identifier.chicagocitationNtsaluba, Kuselo Ntsika. <i>"AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets."</i> ., ,Faculty of Commerce ,African Institute of Financial Markets and Risk Management, 2019. http://hdl.handle.net/11427/31185en_ZA
dc.identifier.citationNtsaluba, K. 2019. AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Ntsaluba, Kuselo Ntsika AB - In this study, a methodology is presented where a hybrid system combining an evolutionary algorithm with artificial neural networks (ANNs) is designed to make weekly directional change forecasts on the USD by inferring a prediction using closing spot rates of three currency pairs: EUR/USD, GBP/USD and CHF/USD. The forecasts made by the genetically trained ANN are compared to those made by a new variation of the simple moving average (MA) trading strategy, tailored to the methodology, as well as a random model. The same process is then repeated for the three major cryptocurrencies namely: BTC/USD, ETH/USD and XRP/USD. The overall prediction accuracy, uptrend and downtrend prediction accuracy is analyzed for all three methods within the fiat currency as well as the cryptocurrency contexts. The best models are then evaluated in terms of their ability to convert predictive accuracy to a profitable investment given an initial investment. The best model was found to be the hybrid model on the basis of overall prediction accuracy and accrued returns. DA - 2019 DB - OpenUCT DP - University of Cape Town KW - Financial Technology LK - https://open.uct.ac.za PY - 2019 T1 - AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets TI - AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets UR - http://hdl.handle.net/11427/31185 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/31185
dc.identifier.vancouvercitationNtsaluba KN. AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets. []. ,Faculty of Commerce ,African Institute of Financial Markets and Risk Management, 2019 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/31185en_ZA
dc.language.rfc3066eng
dc.publisher.departmentAfrican Institute of Financial Markets and Risk Management
dc.publisher.facultyFaculty of Commerce
dc.subjectFinancial Technology
dc.titleAI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationnameMPhil
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_com_2019_ntsaluba_kuselo_ntsika.pdf
Size:
1.24 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Collections