A multivariate approach to heavy flavour tagging with cascade training

Abstract

This paper compares the performance of artificial neural networks and boosted decision trees,with and without cascade training, for tagging b-jets in a collider experiment.It is shown, using a Monte Carlo simulation of WH→lνqq̄ events, that for a b-tagging efficiency of 50%, the light jet rejection power given by boosted decision trees without cascade training is about 55% higher than that given byartificial neural networks. The cascade training technique can improve the performance of boosted decision trees and artificialneural networks at this b-tagging efficiency level by about 35% and 80% respectively. We conclude that the cascade trained boosted decision trees method is themost promising technique for tagging heavy flavours at colliderexperiments.