CaltechAUTHORS
  A Caltech Library Service

Optimization of Signal Significance by Bagging Decision Trees

Narsky, I. (2006) Optimization of Signal Significance by Bagging Decision Trees. In: Statistical Problems in Particle Physics, Astrophysics and Cosmology. Imperial College Press , Singapore, pp. 143-146. ISBN 9781860946493. https://resolver.caltech.edu/CaltechAUTHORS:20190930-110457242

[img] PDF - Accepted Version
See Usage Policy.

173Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190930-110457242

Abstract

An algorithm for optimization of signal significance or any other classification figure of merit (FOM) suited for analysis of HEP data is described. This algorithm trains decision trees on many bootstrap replicas of training data with each tree required to optimize the signal significance or any other chosen FOM. New data are then classified by a simple majority vote of the built trees. The performance of the algorithm has been studied using a search for the radiative leptonic decay B → γlν at BABAR and shown to be superior to that of all other attempted classifiers including such powerful methods as boosted decision trees. In the B → γeν channel, the described algorithm increases the expected signal significance from 2.4σ obtained by an original method designed for the B → γlν analysis to 3.0σ.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1142/9781860948985_0030DOIBook Section
https://arxiv.org/abs/physics/0507157arXivDiscussion Paper
Additional Information:© 2006 Imperial College Press. Work partially supported by Department of Energy under Grant DE-FG03-92-ER40701. Thanks to Frank Porter for comments on a draft of this note.
Funders:
Funding AgencyGrant Number
Department of Energy (DOE)DE-FG03-92-ER40701
Classification Code:PACS numbers: 02.50.Tt, 02.50.Sk, 02.60.Pn
Record Number:CaltechAUTHORS:20190930-110457242
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190930-110457242
Official Citation:OPTIMIZATION OF SIGNAL SIGNIFICANCE BY BAGGING DECISION TREES I. NARSKY Statistical Problems in Particle Physics, Astrophysics and Cosmology. May 2006, 143-146. https://doi.org/10.1142/9781860948985_0030
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:98926
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:07 Oct 2019 23:20
Last Modified:07 Oct 2019 23:20

Repository Staff Only: item control page