Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets
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 a...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
African Institute of Financial Markets and Risk Management
2020
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613194384572416 |
|---|---|
| access_status_str | Open Access |
| author | Ntsaluba, Kuselo Ntsika |
| author2 | Georg, Co-Pierre |
| author_browse | Georg, Co-Pierre Ntsaluba, Kuselo Ntsika |
| author_facet | Georg, Co-Pierre Ntsaluba, Kuselo Ntsika |
| author_sort | Ntsaluba, Kuselo Ntsika |
| collection | Thesis |
| description | 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. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/31185 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:32:13.078Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2020 |
| publishDateRange | 2020 |
| publishDateSort | 2020 |
| publisher | African Institute of Financial Markets and Risk Management |
| publisherStr | African Institute of Financial Markets and Risk Management |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/31185 AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets Ntsaluba, Kuselo Ntsika Georg, Co-Pierre Financial Technology 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. 2020-02-20T09:42:27Z 2020-02-20T09:42:27Z 2019 2020-02-14T08:12:15Z Master Thesis Masters MPhil http://hdl.handle.net/11427/31185 eng application/pdf African Institute of Financial Markets and Risk Management Faculty of Commerce |
| spellingShingle | Financial Technology Ntsaluba, Kuselo Ntsika AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets |
| thesis_degree_str | Master's |
| title | AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets |
| title_full | AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets |
| title_fullStr | AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets |
| title_full_unstemmed | AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets |
| title_short | AI/Machine learning approach to identifying potential statistical arbitrage opportunities with FX and Bitcoin Markets |
| title_sort | ai machine learning approach to identifying potential statistical arbitrage opportunities with fx and bitcoin markets |
| topic | Financial Technology |
| url | http://hdl.handle.net/11427/31185 |
| work_keys_str_mv | AT ntsalubakuselontsika aimachinelearningapproachtoidentifyingpotentialstatisticalarbitrageopportunitieswithfxandbitcoinmarkets |