Joerg Osterrieder

TL;DR: It is found that for the most popular currencies, such as Bitcoin and Litecoin, the generalized hyperbolic distribution gives the best fit, while for the smaller cryptocurrencies the normal inverse Gaussian distribution, generalized t distribution, and Laplace distribution give good fits.

TL;DR: In this article, an univariate extreme value analysis of the returns of Bitcoin is presented, focusing on the tail risk characteristics, and the authors show that the Bitcoin return distribution not only exhibits higher volatility than traditional G10 currencies, but also stronger non-normal characteristics and heavier tails.

TL;DR: It is found that for the most popular currencies, such as Bitcoin and Litecoin, the Generalized hyperbolic distribution gives the best fit, whilst for the smaller cryptocurrencies (determined by market capitalization) the Normal inverse Gaussian distribution, Generalized t distribution, and Laplace distributions give good fits.

TL;DR: Two advanced post-hoc model agnostic explainability techniques called Local Interpretable Model Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) are implemented to machine learning (ML)-based credit scoring models applied to the open-access dataset offered by the US-based P2P Lending Platform, Lending Club.