Matics

In a previous post ( Evolving xPass Models ), we flipped the concept of xPass upside down: instead of asking how hard a pass is, we asked how much defenders make it hard. But there’s a natural counterpart to that idea—evaluating how attacking players …

Early xPass models used basic geometric and contextual features from event data. For instance, StatsBomb’s original xPass used the pass’s start location, end-point distance and angle, whether it was airborne or a cross, previous play actions, and even…

Las tasas de pases completados suelen engañar. No es lo mismo completar un pase corto y sin marca que filtrar uno entre líneas en medio de presión. Por eso se ha desarrollado el modelo expected pass (xPass) , que estima la probabilidad de éxito de cad…