Purpose This study aims to endeavour to decode artificial intelligence (AI)-based tokens' complex dynamics and predictability using a comprehensive multivariate framework that integrates technical and macroeconomic indicators. Design/methodology/approach In this study we used advance machine...

Quantitative investment strategies are often selected from a broad class of candidate models estimated and tested on historical data. Standard statistical techniques to prevent model overfitting such as out-sample backtesting turn out to be unreliable in situations when the selection is based on...