Cryptocurrencies have obtained a crucial position in the international financial landscape. The cryptocurrency market has been perceived as a highly volatile market since the inception of Bitcoin. This study investigates the relevant performance of extreme value models (EVM) in estimating the Value-at-Risk (VaR) of Bitcoin and Ethereum returns. The extreme value mixture models, GPD-Normal-GPD (GNG) and GPD-KDE-GPD models are fitted to the returns of Bitcoin and Ethereum and the Kupiec likelihood backtesting procedure is performed on the VaR estimates to assess the fits. Both models’ results showed that the fits were a much more decent representation of the observed data when compared to the Normal distribution. The backtesting results showed that the GPD-KDE-GPD model’s fit was superior to that of the GPD-Normal-GPD for both sets of returns at all VaR risk levels except at the 99% level. The results of this study may assist with understanding the dynamics and risks associated with cryptocurrencies and can serve as a beneficial tool for decision-making and risk management to investors, traders, financial institutions and many other participants in the cryptocurrency ecosystem.

Current industrial robotic manipulators have made evident their lack of flexibility. The systems must know beforehand the piece and it’s position. To address this issue, contemporary approaches typically employ learning-based techniques, which rely on extensive amounts of data. To obtain vast data, an often sought tool is an extensive grasp dataset. This work introduces our Physics-Based Self-Supervised Grasp Pose Detection (PBSS-GPD) pipeline for model-based grasping point detection, useful to generate grasp pose datasets. Given a gripper-object pair, it samples grasping pose candidates using a modified version of GPD (implementing inner-grasps, CAD support...) and quantifies their quality using the MuJoCo physics engine and a grasp quality metric that takes into account the pose of the object over time. The system is optimised to run on CPU in headless-parallelised mode, with the option of running in a graphical interface or headless and storing videos of the process. The system has been validated obtaining grasping poses for a subset of Egad! objects using the Franka Panda two-finger gripper, compared with state of the art grasp generation pipelines and tested in a real scenario. While our system achieves similar accuracy compared to a contemporary approach, 84% on the real world validation, it has proven to be effective at generating grasps with good centering 18 times faster than the compared system.