AI Paper Atlas

Research map / Time series / Causal and generative time series

TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness

Zhiyuan Zhao, Juntong Ni, Shangqing Xu, Haoxin Liu, Wei Jin, B. Aditya Prakash

ICLR 2026 · Time series › Causal and generative time series · approach: Robust forecasting and evaluation · 7 citations (OpenAlex)

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
exhaustive module-level design space search instead of fixed existing modelsbest existing model · 102 forecasting scenariosMSE: 5.4% error reduction; better in 92 out of 102 scenariosImproved
pick the top searched configuration instead of iTransformeriTransformer · PEMS03 horizon 12MSE: 0.739 -> 0.714Improved
search design space rather than best existing model, rankingbest existing model · 102 forecasting scenariosranking position: 13.66 ranking positionsImproved
use LightGBM model selection top-3 instead of existing best PatchTSTPatchTST · Social_12_SMSE: 0.0994 -> 0.0897Improved
use LightGBM model selection top-3 instead of existing best PatchTSTPatchTST · ETTh1_24_MMSE: 0.2988 -> 0.2963Improved
use LightGBM model selection top-3 instead of existing best DLinearDLinear · Environment_48_SMSE: 0.2950 -> 0.2920Improved
use LightGBM model selection top-3 instead of existing best DLinearDLinear · Security_12_SMSE: 75.2914 -> 74.9425Improved
use a poorly selected configuration (third pick) instead of PatchTSTPatchTST · Social_12_SMSE: 0.0994 -> 0.1310Hurt
use instance normalization on PEMS datasetsforecasting models · PEMSforecasting errorHurt
use instance normalization when shifts are large or seasonality is lowforecasting models · multivariate forecastingforecasting errorImproved
use RNN architectures when HL-ratio is lowforecasting models · multivariate forecastingforecasting errorImproved
use patch embedding with MLP or RNN feed-forward on ETTforecasting models · ETT multivariateforecasting errorImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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