Pinned Repositories
amazon-sagemaker-stock-prediction-archived
Workshop to demonstrate how to apply NN based algorithms to stock market data and forecast price movements.
amazon-sagemaker-time-series-prediction-using-gluonts
CCP
Codes for replicating results in the research paper "Risk-based versus target-based portfolio strategies in the cryptocurrency market"
Conformalized_Quantile_Regression-CQR
Conformalized Quantile Regression
CourseraML_Matlab
MATLAB assignments in Coursera's Machine Learning course
CourseraML_python
I took Andrew Ng's Machine Learning course on Coursera and did the homework assigments... but, on my own in python because I love jupyter notebooks!
CourserML-Fall2013-4thEd-AndrewNg
Coursera-Machine-Learning-Fall2013-4thEd-AndrewNg
Darts
A python library for easy manipulation and forecasting of time series.
DeepAR
Implement Amazon's DeepAR algorithm
DeepJMQR
Deep joint mean and quantile regression for spatio-temporal problems
wl935's Repositories
wl935/mcqrnn-tf2
Monotone composite quantile regression neural network (MCQRNN) with tensorflow 2.x.
wl935/pyquantrf
Here is a [quantile random forest](http://jmlr.org/papers/v7/meinshausen06a.html) implementation that utilizes the [SciKitLearn](https://scikit-learn.org/stable/) RandomForestRegressor. This implementation uses [numba](https://numba.pydata.org) to improve efficiency.
wl935/sedumi
SeDuMi: A linear/quadratic/semidefinite solver for Matlab and Octave
wl935/qp
Quantile Parametrization for probability distribution functions module
wl935/quantnn
Quantile regression neural networks
wl935/Portfolio-Optimization-using-Genetic-Algorithm
Portfolio optimization using Genetic algorithm.
wl935/gluon-ts
Probabilistic time series modeling in Python
wl935/Stock_prediction_AI
In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.
wl935/Darts
A python library for easy manipulation and forecasting of time series.
wl935/End-to-End-Time-Series
This repository hosts code for my Time Series videos part of playlist here - https://www.youtube.com/playlist?list=PL3N9eeOlCrP5cK0QRQxeJd6GrQvhAtpBK
wl935/RobGARCHBoot
wl935/MQRNN
Multi-Quantile Recurrent Neural Network for Quantile Regression
wl935/DeepAR
Implement Amazon's DeepAR algorithm
wl935/Stock-Prediction-Models
Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations
wl935/quantile-regression-tensorflow
Tensorflow implementation of deep quantile regression
wl935/gar-replication
Backtesting Global Growth-at-Risk Replication Files
wl935/mictools
A practical tool for Maximal Information Coefficient (MIC) analysis
wl935/pyfolio
Portfolio and risk analytics in Python
wl935/demand_forecast
wl935/midas_pro
Python version of Mixed Data Sampling (MIDAS) regression (allow for multivariate MIDAS) :golf:
wl935/QR-HFDTD-RNN
Quantile Regression of High-Frequency Data Tail Dynamics via a Recurrent Neural Network
wl935/portfolio_sortino_ratio
This function optimizes portfolio weights based on a user-specified weighted linear combination of the Sortino ratio, Sharpe ratio, average total return, average downside risk, average standard deviation of returns, and max drawdown.
wl935/Xu_Probabilistic_Load_Forecasting
Probabilistic Load Forecasting
wl935/DeepJMQR
Deep joint mean and quantile regression for spatio-temporal problems
wl935/liquidSVM
Support vector machines (SVMs) and related kernel-based learning algorithms are a well-known class of machine learning algorithms, for non-parametric classification and regression. liquidSVM is an implementation of SVMs whose key features are: fully integrated hyper-parameter selection, extreme speed on both small and large data sets, full flexibility for experts, and inclusion of a variety of different learning scenarios: multi-class classification, ROC, and Neyman-Pearson learning, and least-squares, quantile, and expectile regression.
wl935/ppnn
post-processing experiments with neural networks
wl935/W_Zhang_QRNN
QRNN (Quantile Regression Neural Network) Keras version
wl935/multiple_support_vector_machine
MSVR (Multiple Support Vector Regression) python module
wl935/amazon-sagemaker-time-series-prediction-using-gluonts
wl935/amazon-sagemaker-stock-prediction-archived
Workshop to demonstrate how to apply NN based algorithms to stock market data and forecast price movements.