{"id":{"repo_id":"cape-town","oai_identifier":"oai:open.uct.ac.za:11427/31185"},"canonical_url":"https://search.dev.ndltd.org/etd/cape-town/oai:open.uct.ac.za:11427/31185","repository":{"repo_id":"cape-town","name":"University of Cape Town","base_url":"https://open.uct.ac.za/oai/request"},"display":{"title":"AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets","abstract":"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.","abstract_html":"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.","abstract_has_math":false,"creators":["Ntsaluba, Kuselo Ntsika"],"institution":"African Institute of Financial Markets and Risk Management","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Georg, Co-Pierre"],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019","date_published":"2019","updated_at":"2026-07-22T22:22:47Z","subjects":["Financial Technology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11427/31185","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Georg, Co-Pierre"]},{"key":"dc:creator","label":"Author","values":["Ntsaluba, Kuselo Ntsika"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-02-20T09:42:27Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-02-20T09:42:27Z"]},{"key":"dc:date.issued","label":"Date","values":["2019"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["African Institute of Financial Markets and Risk Management"]},{"key":"dc:type","label":"Dc Type","values":["Master Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Masters"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["MPhil"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Financial Technology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11427/31185"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:title","label":"Title","values":["AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets"]}]}],"canonical_facts":{"dc:contributor.advisor":["Georg, Co-Pierre"],"dc:creator":["Ntsaluba, Kuselo Ntsika"],"dc:date.accessioned":["2020-02-20T09:42:27Z"],"dc:date.available":["2020-02-20T09:42:27Z"],"dc:date.issued":["2019"],"dc:description.abstract":["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."],"dc:identifier.uri":["http://hdl.handle.net/11427/31185"],"dc:publisher.department":["African Institute of Financial Markets and Risk Management"],"dc:subject":["Financial Technology"],"dc:title":["AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets"],"dc:type":["Master Thesis"],"dc:type.qualificationlevel":["Masters"],"dc:type.qualificationname":["MPhil"]},"updated_at":"2026-07-22T22:22:47Z"}