Predictive Time Series Analytics at Scale

About

From autonomous driving to industrial IoT, the age of billions of intelligent devices generating time-varying data is here. There is a growing need to ingest and analyze time series data accurately and efficiently to look for interesting patterns at scale. Our key goal in Metronome is to build novel data management, machine learning, and interactive visualization techniques for supporting the development and deployment of predictive time series analytics applications, such as anomaly detection.

Publications

“Visual Exploration of Time Series Anomalies with Metro-Viz”
Philipp Eichmann, Franco Solleza, Junjay Tan, Nesime Tatbul, Stan Zdonik
SigMOD Demo. 2019. Best Demo Award

“Metro-Viz: Black-Box Analysis of Time Series Anomaly Detectors”
Philipp Eichmann, Franco Solleza, Junjay Tan, Nesime Tatbul, Stan Zdonik
SigCHI. 2019.

“Precision and Recall for Time Series”
Nesime Tatbul, Tae Jun Lee, Stan Zdonik, Mejbah Alam, Justin Gottschlich
NeurIPS Spotlight Paper. 2018.
Code: TSAD-Evaluator

“Greenhouse: A Zero-Positive Machine Learning System for Time-Series Anomaly Detection”
Tae-Jun Lee, Justin Gottschlich, Nesime Tatbul, Eric Metcalf, Stan Zdonik
SysML. 2018.

“Precision and Recall for Range-Based Anomaly Detection”
Tae-Jun Lee, Justin Gottschlich, Nesime Tatbul, Eric Metcalf, Stan Zdonik
SysML. 2018.

“Data Ingestion for the Connected World”
John Meehan, Cansu Aslantas, Jiang Du, Nesime Tatbul, Stan Zdonik
CIDR. 2017.

Team

Philipp Eichmann	Franco Solleza	Stan Zdonik	Nesime Tatbul
Brown University	Brown University	Brown University	Intel Labs and MIT

Mejbah Alam	Justin Gottschlich
Intel Labs	Intel Labs

Alumni

Tae Jun Lee	Eric Metcalf	John Meehan
Microsoft	Awake Security	Tranquil Data

Acknowledgements

		grant IIS-1526639