Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree

TL;DR

This paper introduces a 'bonsai' boosted decision tree that enhances high-level triggering in particle physics by being more efficient, robust, and faster than traditional methods, suitable for real-time data acquisition systems.

Contribution

The paper presents a modified BDT, called 'bonsai' BDT, which improves efficiency, robustness, and speed for high-level triggering in particle physics experiments.

Findings

More efficient than traditional cut-based methods

Robust against detector instabilities

Very fast for online processing

Abstract

High-level triggering is a vital component in many modern particle physics experiments. This paper describes a modification to the standard boosted decision tree (BDT) classifier, the so-called "bonsai" BDT, that has the following important properties: it is more efficient than traditional cut-based approaches; it is robust against detector instabilities, and it is very fast. Thus, it is fit-for-purpose for the online running conditions faced by any large-scale data acquisition system.