A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning …

helpers for teaching materials in python at the ENSAE

Code and output for Master Thesis "A leveraged investment strategy using Deep Reinforcement Learning"

Master Thesis "Modelling Systemic Risk using Neural Network Quantile Regression"

Quantile Neural Network Test

RStudio Cheat Sheets

Variational Bayes

Project for the SFM1 class

Time series classification using PCA+SVM

Independent Component Analysis

Boosted Sparse and Low-Rank Tensor Regression

Quantlets for Master Thesis of Michael Kostmann

Code accompanying the Anatolyev, S. and Barunik, J. (2018): Forecasting dynamic return distributions based on ordered binary choice and cross-quantile predictability connection, manuscript

Code for Markov Chain Regime Switching models including GARCH processes in the regimes

This is the application of TopDown, BottomUp and PrincipalExpectile algorithms to the Chinese weather data

Trust region nonlinear optimization, efficient for sparse Hessians

Perform tensor-on-tensor regression