TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning
For network operators and researchers, TRACE provides a method to detect routing instability without relying on control plane information, which is often inaccessible.
TRACE uses only traceroute latency data to detect Internet route changes, achieving superior F1-score performance over traditional baselines by employing a stacked ensemble of Gradient Boosted Decision Trees with calibrated decision thresholds.
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.