Quant Mashup - Hudson and Thames Model Interpretability: The Model Fingerprint Algorithm [Hudson and Thames]“The complexity of machine learning models presents a substantial barrier to their adoption for many investors. The algorithms that generate machine learning predictions are sometimes regarded as a black box and demand interpretation. Yimou Li, David Turkington, and Alireza Yazdani present a(...) The Hierarchical Risk Parity Algorithm: An Introduction [Hudson and Thames]Portfolio Optimisation has always been a hot topic of research in financial modelling and rightly so – a lot of people and companies want to create and manage an optimal portfolio which gives them good returns. There is an abundance of mathematical literature dealing with this topic such as the(...) Bagging in Financial Machine Learning: Sequential Bootstrapping [Hudson and Thames]To understand the Sequential Bootstrapping algorithm and why it is so crucial in financial machine learning, first we need to recall what bagging and bootstrapping is – and how ensemble machine learning models (Random Forest, ExtraTrees, GradientBoosted Trees) work. It all starts from a Decision(...) The Single Futures Roll [Hudson and Thames]Building trading strategies on futures contracts has the unique problem that a given contract has expiration date, example the 3 month contract on wheat. In order to build a continuous time series across the different contracts we stitch them together, most commonly using an auto roll or some other(...) Does Meta-Labeling Add to Signal Efficacy? [Hudson and Thames]Successful and long-lasting quantitative research programs require a solid foundation that includes procurement and curation of data, creation of building blocks for feature engineering, state of the art methodologies, and backtesting. In this project we create a open-source python package(...)