Representation Learning for Regime detection in Block Hierarchical Financial Markets
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912093917151232 |
|---|---|
| author | Orton, Alexa Gebbie, Tim |
| author_facet | Orton, Alexa Gebbie, Tim |
| contents | We consider financial market regime detection from the perspective of deep representation learning of the causal information geometry underpinning traded asset systems using a hierarchical correlation structure to characterise market evolution. We assess the robustness of three toy models: SPDNet, SPD-NetBN and U-SPDNet whose architectures respect the underlying Riemannian manifold of input block hierarchical SPD correlation matrices. Market phase detection for each model is carried out using three data configurations: randomised JSE Top 60 data, synthetically-generated block hierarchical SPD matrices and block-resampled chronology-preserving JSE Top 60 data. We show that using a singular performance metric is misleading in our financial market investment use cases where deep learning models overfit in learning spatio-temporal correlation dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22346 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Representation Learning for Regime detection in Block Hierarchical Financial Markets Orton, Alexa Gebbie, Tim Statistical Finance Machine Learning We consider financial market regime detection from the perspective of deep representation learning of the causal information geometry underpinning traded asset systems using a hierarchical correlation structure to characterise market evolution. We assess the robustness of three toy models: SPDNet, SPD-NetBN and U-SPDNet whose architectures respect the underlying Riemannian manifold of input block hierarchical SPD correlation matrices. Market phase detection for each model is carried out using three data configurations: randomised JSE Top 60 data, synthetically-generated block hierarchical SPD matrices and block-resampled chronology-preserving JSE Top 60 data. We show that using a singular performance metric is misleading in our financial market investment use cases where deep learning models overfit in learning spatio-temporal correlation dynamics. |
| title | Representation Learning for Regime detection in Block Hierarchical Financial Markets |
| topic | Statistical Finance Machine Learning |
| url | https://arxiv.org/abs/2410.22346 |