Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Jump detection tests in financial time series ? a deep learning approach
In most financial market models, the asset price is driven by continuous Brownian motion. An additional complexity to such a model is the inclusion of a discontinuous jump process. Jumps are theorised to be rare, sudden, and thought to be the result of the market reacting to new information. Jump te...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Finance and Tax
2024
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613474168766464 |
|---|---|
| access_status_str | Open Access |
| author | Wagener, Justin |
| author2 | Ouwehand, Peter |
| author_browse | Ouwehand, Peter Wagener, Justin |
| author_facet | Ouwehand, Peter Wagener, Justin |
| author_sort | Wagener, Justin |
| collection | Thesis |
| description | In most financial market models, the asset price is driven by continuous Brownian motion. An additional complexity to such a model is the inclusion of a discontinuous jump process. Jumps are theorised to be rare, sudden, and thought to be the result of the market reacting to new information. Jump tests are identified as crucial to understand market incompleteness arising from this discontinuity. Across studies, the Lee and Mykland (2007) method emerges as one of the strongest performers in jump detection. This serves as the benchmark to the jump tests created in this dissertation. The first uses a Long Short-Term Memory (LSTM) neural network based supervised learning approach. The second uses unsupervised learning in the form of a Convolutional Neural Network (CNN) autoencoder. Bates, Merton and Stochastic Volatility double Jump (SVJJ) models provide the data used for comparison. For supervised learning, synthetic data is essential as jump labels are needed for training. The autoencoder jump test is an improvement as it does not need labelled jumps to train. This was found to be the best jump test overall when compared out of sample. Both methods were found to beat the benchmark set by Lee and Mykland (2007). The performance metrics used are suited to the imbalanced data sets arising from the assumption of jumps being rare. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/40201 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:36:43.289Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| publisher | Department of Finance and Tax |
| publisherStr | Department of Finance and Tax |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/40201 Jump detection tests in financial time series ? a deep learning approach Wagener, Justin Ouwehand, Peter Finance and Tax In most financial market models, the asset price is driven by continuous Brownian motion. An additional complexity to such a model is the inclusion of a discontinuous jump process. Jumps are theorised to be rare, sudden, and thought to be the result of the market reacting to new information. Jump tests are identified as crucial to understand market incompleteness arising from this discontinuity. Across studies, the Lee and Mykland (2007) method emerges as one of the strongest performers in jump detection. This serves as the benchmark to the jump tests created in this dissertation. The first uses a Long Short-Term Memory (LSTM) neural network based supervised learning approach. The second uses unsupervised learning in the form of a Convolutional Neural Network (CNN) autoencoder. Bates, Merton and Stochastic Volatility double Jump (SVJJ) models provide the data used for comparison. For supervised learning, synthetic data is essential as jump labels are needed for training. The autoencoder jump test is an improvement as it does not need labelled jumps to train. This was found to be the best jump test overall when compared out of sample. Both methods were found to beat the benchmark set by Lee and Mykland (2007). The performance metrics used are suited to the imbalanced data sets arising from the assumption of jumps being rare. 2024-07-02T10:13:59Z 2024-07-02T10:13:59Z 2023 2024-06-05T13:54:09Z Thesis / Dissertation Masters MPhil http://hdl.handle.net/11427/40201 eng application/pdf Department of Finance and Tax Faculty of Commerce |
| spellingShingle | Finance and Tax Wagener, Justin Jump detection tests in financial time series ? a deep learning approach |
| thesis_degree_str | Master's |
| title | Jump detection tests in financial time series ? a deep learning approach |
| title_full | Jump detection tests in financial time series ? a deep learning approach |
| title_fullStr | Jump detection tests in financial time series ? a deep learning approach |
| title_full_unstemmed | Jump detection tests in financial time series ? a deep learning approach |
| title_short | Jump detection tests in financial time series ? a deep learning approach |
| title_sort | jump detection tests in financial time series a deep learning approach |
| topic | Finance and Tax |
| url | http://hdl.handle.net/11427/40201 |
| work_keys_str_mv | AT wagenerjustin jumpdetectiontestsinfinancialtimeseriesadeeplearningapproach |