TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning

TL;DR

TRACE is a machine learning pipeline that detects Internet route changes using traceroute latency data alone, employing ensemble learning and feature engineering to outperform baseline models.

Contribution

It introduces a novel ML approach with ensemble learning and specialized feature engineering for route change detection without control plane data.

Findings

TRACE achieves higher F1-score than baseline models.

The ensemble approach effectively detects rare routing events.

Feature engineering captures temporal dynamics for improved accuracy.

Abstract

Detecting Internet routing instability is a critical yet challenging task, particularly when relying solely on endpoint active measurements. This study introduces TRACE, a MachineLearning (ML)pipeline designed to identify route changes using only traceroute latency data, thereby ensuring independence from control plane information. We propose a robust feature engineering strategy that captures temporal dynamics using rolling statistics and aggregated context patterns. The architecture leverages a stacked ensemble of Gradient Boosted Decision Trees refined by a hyperparameter-optimized meta-learner. By strictly calibrating decision thresholds to address the inherent class imbalance of rare routing events, TRACE achieves a superior F1-score performance, significantly outperforming traditional baseline models and demonstrating strong effective ness in detecting routing changes on the Internet.