SLIDR — Real-Time Robotic Traffic Detection
SLIDR (Scalable Learning-based Invalid click Detection in Real-time) is Amazon's neural system for detecting robotic traffic in online advertising. It was presented at IAAI 2023.
Files
SLIDR System Diagram (Graphviz source)
A Graphviz digraph describing the full SLIDR architecture across five
clusters:
- IAAI 2023 — conference context and related publications
- SLIDR — the paper, the system name, and its Amazon context
- Model development — challenges, labels, metrics (invalidation rate, false-positive rate, robotic coverage), and the neural model's input features (user frequency/velocity counters, entity counters, time of click, logged-in status)
- Model deployment — calibration, full-traffic vs traffic-slice evaluation, the offline system, real-time inference service, feature values, guardrails, and disaster-recovery mechanisms
- Future work — learned representations and deep-and-cross networks
SLIDR System Diagram (rendered PNG)
Rendered output of the Graphviz source above. The diagram uses colour coding to distinguish architectural layers: blue for context nodes, green for metrics, yellow for model components, orange for calibration, pink for deployment, and purple for future directions.
Background
SLIDR addresses the challenge of distinguishing human from robotic ad clicks at Amazon scale. Key design decisions include:
- User-level frequency and velocity counters as primary features
- Separate offline training and real-time inference paths
- Calibration against full traffic and targeted traffic slices
- Guardrails and disaster-recovery to maintain advertiser trust
Reference
Amazon / IAAI 2023 — "Real-time Detection of Robotic Traffic in Online Advertising"