AI Paper Atlas

Research map / Time series / Causal and generative time series

Merlion: End-to-End Machine Learning for Time Series

Aadyot Bhatnagar, Paul Kassianik, Chenghao Liu, Tian Lan, Wenzhuo Yang, Rowan Cassius, Doyen Sahoo, Devansh Arpit, Sri Subramanian, Gerald Woo, Amrita Saha, Arun Kumar Jagota and 11 more

JMLR 2023 · Time series › Causal and generative time series · approach: Robust forecasting and evaluation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add AutoML hyperparameter selectionARIMA (AutoSARIMA) · m4-hourmean sMAPE: 33.54 -> 13.61Improved
add AutoML hyperparameter selectionARIMA (AutoSARIMA) · m4-yearmean sMAPE: 16.37 -> 17.16Hurt
add AutoML hyperparameter selectionProphet (AutoProphet) · m4-hourmean sMAPE: 18.08 -> 16.49Improved
add AutoML hyperparameter selectionProphet (AutoProphet) · internal3mean sMAPE: 72.55 -> 69.32Improved
add AutoML hyperparameter selectionProphet (AutoProphet) · internal1mean sMAPE: 56.07 -> 56.43Hurt
add AutoML hyperparameter selectionETS (AutoETS) · m4-hourmean sMAPE: 42.95 -> 19.23Improved
add AutoML hyperparameter selectionETS (AutoETS) · internal1mean sMAPE: 17.02 -> 21.65Hurt
add AutoML hyperparameter selectionETS (AutoETS) · m4-daymean sMAPE: 3.04 -> 3.07No clear effect
ensemble calibrated scores of AutoETS, RRCF and ZMS instead of the single AutoETSanomaly detector · NABF1: 0.350 -> 0.548Improved
ensemble calibrated scores of AutoETS, RRCF and ZMS instead of the single RRCFanomaly detector · UCRF1: 0.568 -> 0.476Hurt
ensemble calibrated scores of AutoETS, RRCF and ZMS instead of the single ZMSanomaly detector · internalF1: 0.486 -> 0.500No clear effect
ensemble calibrated scores instead of ARIMAanomaly detector · average gap to best F1delta F1 vs best: 0.148 ± 0.099 -> 0.034 ± 0.044Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy