{"id":{"repo_id":"cape-town","oai_identifier":"oai:open.uct.ac.za:11427/41861"},"canonical_url":"https://search.dev.ndltd.org/etd/cape-town/oai:open.uct.ac.za:11427/41861","repository":{"repo_id":"cape-town","name":"University of Cape Town","base_url":"https://open.uct.ac.za/oai/request"},"display":{"title":"Representation learning for regime detection in financial markets","abstract":"We investigate financial market regime detection from the perspective of deep representation learning of the causal (reflexive) information geometry underpinning complex (multi-scale) dynamical traded asset systems using an emergent hierarchical correlation structure to characterise evolving macroeconomic market phases. Specifically, we assess the robustness of three toy models: SPD Matrix Network (SPDNet), SPD Matrix Network with Riemannian Batch Normalisation (SPDNetBN) and U-shaped SPD Matrix Network (U-SPDNet) whose architectures respect the underlying Riemannian manifold of input block hierarchical Symmetric Positive Definite (SPD) correlation matrices by employing Log-Euclidean Metric (LEM)s. Market phase detection for each model is carried out using three data configurations: i.) Randomised Johannesburg Stock Exchange (JSE) Top 60 data, ii.) synthetically-generated block hierarchical SPD matrices, and iii.) chronology-preserving block-resampled JSE Top 60 data. We show that using a singular performance metric is misleading in our financial market use cases. We confirm that U-SPDNet performs improved latent feature extraction with better classification performance in stressed and rally market phases, despite achieving lower Out-of-Sample (OOS) backtest scenario accuracy than that of the benchmark SPDNet. The SPDNet-based models fail in capturing latent reflexive spatio-temporal block hierarchical correlation dynamics and deliver corner solutions across all input data sets. The U-SPDNet is promising in terms of its utility in regime dependent portfolio optimisation strategy generation as a model better-suited to capturing latent block hierarchical correlation structures arising from lead-lag causal feedback information loops that often drive the evolution of evolving market regimes","abstract_html":"We investigate financial market regime detection from the perspective of deep representation learning of the causal (reflexive) information geometry underpinning complex (multi-scale) dynamical traded asset systems using an emergent hierarchical correlation structure to characterise evolving macroeconomic market phases. Specifically, we assess the robustness of three toy models: SPD Matrix Network (SPDNet), SPD Matrix Network with Riemannian Batch Normalisation (SPDNetBN) and U-shaped SPD Matrix Network (U-SPDNet) whose architectures respect the underlying Riemannian manifold of input block hierarchical Symmetric Positive Definite (SPD) correlation matrices by employing Log-Euclidean Metric (LEM)s. Market phase detection for each model is carried out using three data configurations: i.) Randomised Johannesburg Stock Exchange (JSE) Top 60 data, ii.) synthetically-generated block hierarchical SPD matrices, and iii.) chronology-preserving block-resampled JSE Top 60 data. We show that using a singular performance metric is misleading in our financial market use cases. We confirm that U-SPDNet performs improved latent feature extraction with better classification performance in stressed and rally market phases, despite achieving lower Out-of-Sample (OOS) backtest scenario accuracy than that of the benchmark SPDNet. The SPDNet-based models fail in capturing latent reflexive spatio-temporal block hierarchical correlation dynamics and deliver corner solutions across all input data sets. The U-SPDNet is promising in terms of its utility in regime dependent portfolio optimisation strategy generation as a model better-suited to capturing latent block hierarchical correlation structures arising from lead-lag causal feedback information loops that often drive the evolution of evolving market regimes","abstract_has_math":false,"creators":["Orton, Alexa"],"institution":"Department of Statistical Sciences","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Gebbie, Timothy"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-22T22:22:37Z","subjects":["deep manifold representation learning","SPD matrix classification","nested block hierarchical financial market correlations","regime detection","causal feedback loops"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11427/41861","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Gebbie, Timothy"]},{"key":"dc:creator","label":"Author","values":["Orton, Alexa"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-18T10:53:18Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-18T10:53:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Department of Statistical Sciences"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["Universiy of Cape Town"]},{"key":"dc:type","label":"Dc Type","values":["Thesis / Dissertation"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Masters","PhD"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["deep manifold representation learning","SPD matrix classification","nested block hierarchical financial market correlations","regime detection","causal feedback loops"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11427/41861"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We investigate financial market regime detection from the perspective of deep representation learning of the causal (reflexive) information geometry underpinning complex (multi-scale) dynamical traded asset systems using an emergent hierarchical correlation structure to characterise evolving macroeconomic market phases. Specifically, we assess the robustness of three toy models: SPD Matrix Network (SPDNet), SPD Matrix Network with Riemannian Batch Normalisation (SPDNetBN) and U-shaped SPD Matrix Network (U-SPDNet) whose architectures respect the underlying Riemannian manifold of input block hierarchical Symmetric Positive Definite (SPD) correlation matrices by employing Log-Euclidean Metric (LEM)s. Market phase detection for each model is carried out using three data configurations: i.) Randomised Johannesburg Stock Exchange (JSE) Top 60 data, ii.) synthetically-generated block hierarchical SPD matrices, and iii.) chronology-preserving block-resampled JSE Top 60 data. We show that using a singular performance metric is misleading in our financial market use cases. We confirm that U-SPDNet performs improved latent feature extraction with better classification performance in stressed and rally market phases, despite achieving lower Out-of-Sample (OOS) backtest scenario accuracy than that of the benchmark SPDNet. The SPDNet-based models fail in capturing latent reflexive spatio-temporal block hierarchical correlation dynamics and deliver corner solutions across all input data sets. The U-SPDNet is promising in terms of its utility in regime dependent portfolio optimisation strategy generation as a model better-suited to capturing latent block hierarchical correlation structures arising from lead-lag causal feedback information loops that often drive the evolution of evolving market regimes"]},{"key":"dc:title","label":"Title","values":["Representation learning for regime detection in financial markets"]}]}],"canonical_facts":{"dc:contributor.advisor":["Gebbie, Timothy"],"dc:creator":["Orton, Alexa"],"dc:date.accessioned":["2025-09-18T10:53:18Z"],"dc:date.available":["2025-09-18T10:53:18Z"],"dc:date.issued":["2025"],"dc:description.abstract":["We investigate financial market regime detection from the perspective of deep representation learning of the causal (reflexive) information geometry underpinning complex (multi-scale) dynamical traded asset systems using an emergent hierarchical correlation structure to characterise evolving macroeconomic market phases. Specifically, we assess the robustness of three toy models: SPD Matrix Network (SPDNet), SPD Matrix Network with Riemannian Batch Normalisation (SPDNetBN) and U-shaped SPD Matrix Network (U-SPDNet) whose architectures respect the underlying Riemannian manifold of input block hierarchical Symmetric Positive Definite (SPD) correlation matrices by employing Log-Euclidean Metric (LEM)s. Market phase detection for each model is carried out using three data configurations: i.) Randomised Johannesburg Stock Exchange (JSE) Top 60 data, ii.) synthetically-generated block hierarchical SPD matrices, and iii.) chronology-preserving block-resampled JSE Top 60 data. We show that using a singular performance metric is misleading in our financial market use cases. We confirm that U-SPDNet performs improved latent feature extraction with better classification performance in stressed and rally market phases, despite achieving lower Out-of-Sample (OOS) backtest scenario accuracy than that of the benchmark SPDNet. The SPDNet-based models fail in capturing latent reflexive spatio-temporal block hierarchical correlation dynamics and deliver corner solutions across all input data sets. The U-SPDNet is promising in terms of its utility in regime dependent portfolio optimisation strategy generation as a model better-suited to capturing latent block hierarchical correlation structures arising from lead-lag causal feedback information loops that often drive the evolution of evolving market regimes"],"dc:identifier.uri":["http://hdl.handle.net/11427/41861"],"dc:publisher.department":["Department of Statistical Sciences"],"dc:publisher.institution":["Universiy of Cape Town"],"dc:subject":["deep manifold representation learning","SPD matrix classification","nested block hierarchical financial market correlations","regime detection","causal feedback loops"],"dc:title":["Representation learning for regime detection in financial markets"],"dc:type":["Thesis / Dissertation"],"dc:type.qualificationlevel":["Masters","PhD"]},"updated_at":"2026-07-22T22:22:37Z"}