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

TL;DR

RAMSeS is a framework that adaptively selects and ensembles time-series anomaly detection models, improving performance across diverse datasets by combining genetic algorithms, Bayesian techniques, and robustness testing.

Contribution

Introduces RAMSeS, a novel adaptive framework combining ensemble and model selection strategies for robust time-series anomaly detection across domains.

Findings

Outperforms prior methods on F1 score.

Effectively adapts to dataset-specific characteristics.

Leverages multiple models for improved detection.

Abstract

Time-series data vary widely across domains, making a universal anomaly detector impractical. Methods that perform well on one dataset often fail to transfer because what counts as an anomaly is context dependent. The key challenge is to design a method that performs well in specific contexts while remaining adaptable across domains with varying data complexities. We present the Robust and Adaptive Model Selection for Time-Series Anomaly Detection RAMSeS framework. RAMSeS comprises two branches: (i) a stacking ensemble optimized with a genetic algorithm to leverage complementary detectors. (ii) An adaptive model-selection branch identifies the best single detector using techniques including Thompson sampling, robustness testing with generative adversarial networks, and Monte Carlo simulations. This dual strategy exploits the collective strength of multiple models and adapts to dataset-specific characteristics. We evaluate RAMSeS and show that it outperforms prior methods on F1.