Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Online Non-linear Prediction of Financial Time Series Patterns
We consider a mechanistic non-linear machine learning approach to learning signals in financial time series data. A modularised and decoupled algorithm framework is established and is proven on daily sampled closing time-series data for JSE equity markets. The input patterns are based on input data...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Statistical Sciences
2020
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613312069402624 |
|---|---|
| access_status_str | Open Access |
| author | da Costa, Joel |
| author2 | Gebbie, Timothy |
| author_browse | Gebbie, Timothy da Costa, Joel |
| author_facet | Gebbie, Timothy da Costa, Joel |
| author_sort | da Costa, Joel |
| collection | Thesis |
| description | We consider a mechanistic non-linear machine learning approach to learning signals in financial time series data. A modularised and decoupled algorithm framework is established and is proven on daily sampled closing time-series data for JSE equity markets. The input patterns are based on input data vectors of data windows preprocessed into a sequence of daily, weekly and monthly or quarterly sampled feature measurement changes (log feature fluctuations). The data processing is split into a batch processed step where features are learnt using a Stacked AutoEncoder (SAE) via unsupervised learning, and then both batch and online supervised learning are carried out on Feedforward Neural Networks (FNNs) using these features. The FNN output is a point prediction of measured time-series feature fluctuations (log differenced data) in the future (ex-post). Weight initializations for these networks are implemented with restricted Boltzmann machine pretraining, and variance based initializations. The validity of the FNN backtest results are shown under a rigorous assessment of backtest overfitting using both Combinatorially Symmetrical Cross Validation and Probabilistic and Deflated Sharpe Ratios. Results are further used to develop a view on the phenomenology of financial markets and the value of complex historical data under unstable dynamics. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/32221 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:34:08.683Z |
| 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 | Department of Statistical Sciences |
| publisherStr | Department of Statistical Sciences |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/32221 Online Non-linear Prediction of Financial Time Series Patterns da Costa, Joel Gebbie, Timothy online learning feedforward neural network restricted Boltzmann machine variance weight initialization stacked autoencoder pattern prediction JSE non-linear financial time series combinatorially symmetrical cross validation backtest overfitting deflated Sharpe ratio probabilistic Sharpe ratio We consider a mechanistic non-linear machine learning approach to learning signals in financial time series data. A modularised and decoupled algorithm framework is established and is proven on daily sampled closing time-series data for JSE equity markets. The input patterns are based on input data vectors of data windows preprocessed into a sequence of daily, weekly and monthly or quarterly sampled feature measurement changes (log feature fluctuations). The data processing is split into a batch processed step where features are learnt using a Stacked AutoEncoder (SAE) via unsupervised learning, and then both batch and online supervised learning are carried out on Feedforward Neural Networks (FNNs) using these features. The FNN output is a point prediction of measured time-series feature fluctuations (log differenced data) in the future (ex-post). Weight initializations for these networks are implemented with restricted Boltzmann machine pretraining, and variance based initializations. The validity of the FNN backtest results are shown under a rigorous assessment of backtest overfitting using both Combinatorially Symmetrical Cross Validation and Probabilistic and Deflated Sharpe Ratios. Results are further used to develop a view on the phenomenology of financial markets and the value of complex historical data under unstable dynamics. 2020-09-11T09:28:42Z 2020-09-11T09:28:42Z 2020 2020-09-11T09:28:28Z Master Thesis Masters MSc http://hdl.handle.net/11427/32221 eng application/pdf Department of Statistical Sciences Faculty of Science |
| spellingShingle | online learning feedforward neural network restricted Boltzmann machine variance weight initialization stacked autoencoder pattern prediction JSE non-linear financial time series combinatorially symmetrical cross validation backtest overfitting deflated Sharpe ratio probabilistic Sharpe ratio da Costa, Joel Online Non-linear Prediction of Financial Time Series Patterns |
| thesis_degree_str | Master's |
| title | Online Non-linear Prediction of Financial Time Series Patterns |
| title_full | Online Non-linear Prediction of Financial Time Series Patterns |
| title_fullStr | Online Non-linear Prediction of Financial Time Series Patterns |
| title_full_unstemmed | Online Non-linear Prediction of Financial Time Series Patterns |
| title_short | Online Non-linear Prediction of Financial Time Series Patterns |
| title_sort | online non linear prediction of financial time series patterns |
| topic | online learning feedforward neural network restricted Boltzmann machine variance weight initialization stacked autoencoder pattern prediction JSE non-linear financial time series combinatorially symmetrical cross validation backtest overfitting deflated Sharpe ratio probabilistic Sharpe ratio |
| url | http://hdl.handle.net/11427/32221 |
| work_keys_str_mv | AT dacostajoel onlinenonlinearpredictionoffinancialtimeseriespatterns |