Using Random Forests to Classify W+W- and ttbar Events

TL;DR

This paper demonstrates that a random forest classifier effectively distinguishes W+W- from ttbar events in proton-proton collisions, outperforming traditional methods and reducing systematic uncertainties, even with incomplete data.

Contribution

The study introduces a random forest approach for classifying collider events, showing improved accuracy and robustness over standard cut-based analyses.

Findings

Random forest outperforms cut-based analysis in event classification.

Distribution distortions are minimal, potentially reducing systematic uncertainties.

Classifier maintains performance with missing features like transverse energy.

Abstract

We have carried out an exercise in the classification of W+W- and ttbar events as produced in a high-energy proton-proton collider, motivated in part by the current tension between the measured and predicted values of the WW cross section. The performance of the random forest classifier surpasses that of a standard cut-based analysis. Furthermore, the distortion of the distributions of key kinematic event features is relatively slight, suggesting that systematic uncertainties due to modeling might be reduced. Finally, our random forest can tolerate missing features such as missing transverse energy without a severe degradation of its performance.