RAMSeS: Robust and Adaptive Model Selection for Time-Series Anomaly Detection Algorithms

RAMSeS addresses the challenge of automatically selecting the most suitable anomaly detection algorithm for time-series data. The framework is both robust — handling noisy and diverse datasets — and adaptive — adjusting model selection strategies based on data characteristics. This work contributes to making time-series anomaly detection more reliable and practical in real-world deployments.

Authors: Mohamed Abdelmaksoud, Sheng Ding, Andrey Morozov, Ziawasch Abedjan

Venue: IEEE International Conference on Data Engineering (ICDE), 2026

Recommended citation: Abdelmaksoud, Mohamed, Sheng Ding, Andrey Morozov, and Ziawasch Abedjan. "RAMSeS: Robust and Adaptive Model Selection for Time-Series Anomaly Detection Algorithms." ICDE. 2026.