AlexaOrton

BH-SPD-CorrMat-Nets

We perform market regime detection by testing three deep representation learning models tailored to the SPD Riemannian manifold of correlation matrices constructed from Bloomberg JSE Top 60 traded stock price returns data and synthetically-generated block hierarchical correlation matrices.

BH-SPDNet

Market regime detection is performed by comparing the performance of three deep representation learning models: SPDNet, SPDNetBN and U-SPDNet. Both hierarchically-ordered JSE Top 60 returns and synthetically-generated block hierarchical correlation matrices are used as input to the learning process.

deep-learning-BH-market-data

Real-world and synthetic block hierarchical correlation matrices generated for the training and validation of SPDNet, SPDNetBN and U-SPDNet models.

FSD-First-Repository-

Learning how to use Github for version control

GRAE

Geometry Regularized Autoencoders (GRAE) for large-scale visualization and manifold learning

handson-ml2

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

Machine-Learning-for-Algorithmic-Trading-Second-Edition

Code and resources for Machine Learning for Algorithmic Trading, 2nd edition.

microprediction

pyRMT

Python library for Random Matrix Theory, cleaning schemes for correlation matrices, and portfolio optimization

timeseries_generator

correlated timeseries generative models

AlexaOrton/BH-SPD-CorrMat-Nets

We perform market regime detection by testing three deep representation learning models tailored to the SPD Riemannian manifold of correlation matrices constructed from Bloomberg JSE Top 60 traded stock price returns data and synthetically-generated block hierarchical correlation matrices.

AlexaOrton/BH-SPDNet

Market regime detection is performed by comparing the performance of three deep representation learning models: SPDNet, SPDNetBN and U-SPDNet. Both hierarchically-ordered JSE Top 60 returns and synthetically-generated block hierarchical correlation matrices are used as input to the learning process.

AlexaOrton/deep-learning-BH-market-data

Real-world and synthetic block hierarchical correlation matrices generated for the training and validation of SPDNet, SPDNetBN and U-SPDNet models.

AlexaOrton/FSD-First-Repository-

Learning how to use Github for version control

AlexaOrton/GRAE

Geometry Regularized Autoencoders (GRAE) for large-scale visualization and manifold learning

AlexaOrton/handson-ml2

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

AlexaOrton/Machine-Learning-for-Algorithmic-Trading-Second-Edition

Code and resources for Machine Learning for Algorithmic Trading, 2nd edition.

AlexaOrton/microprediction

AlexaOrton/pyRMT

Python library for Random Matrix Theory, cleaning schemes for correlation matrices, and portfolio optimization

AlexaOrton/timeseries_generator

correlated timeseries generative models

AlexaOrton/svhc