ECoLAD: Deployment-Oriented Evaluation for Automotive Time-Series Anomaly Detection
This addresses deployment challenges for automotive anomaly detection, but it is incremental as it focuses on evaluation protocols rather than new methods.
The paper tackled the problem that accuracy-only evaluations misrepresent the feasibility of time-series anomaly detectors for in-vehicle deployment, which requires predictable latency and limited CPU parallelism, and found that lightweight classical detectors maintained coverage and detection lift under constraints while several deep methods lost feasibility before accuracy.
Time-series anomaly detectors are commonly compared on workstation-class hardware under unconstrained execution. In-vehicle monitoring, however, requires predictable latency and stable behavior under limited CPU parallelism. Accuracy-only leaderboards can therefore misrepresent which methods remain feasible under deployment-relevant constraints. We present ECoLAD (Efficiency Compute Ladder for Anomaly Detection), a deployment-oriented evaluation protocol instantiated as an empirical study on proprietary automotive telemetry (anomaly rate ${\approx}$0.022) and complementary public benchmarks. ECoLAD applies a monotone compute-reduction ladder across heterogeneous detector families using mechanically determined, integer-only scaling rules and explicit CPU thread caps, while logging every applied configuration change. Throughput-constrained behavior is characterized by sweeping target scoring rates and reporting (i) coverage (the fraction of entities meeting the target) and (ii) the best AUC-PR achievable among measured ladder configurations satisfying the target. On constrained automotive telemetry, lightweight classical detectors sustain both coverage and detection lift above the random baseline across the full throughput sweep. Several deep methods lose feasibility before they lose accuracy.