ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Arango, Sebastian Pineda, Mercado, Pedro, Kapoor, Shubham, Ansari, Abdul Fatir, Stella, Lorenzo, Shen, Huibin, Senetaire, Hugo, Turkmen, Caner, Shchur, Oleksandr, Maddix, Danielle C., Bohlke-Schneider, Michael, Wang, Yuyang, Rangapuram, Syama Sundar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916653512523776
author Arango, Sebastian Pineda
Mercado, Pedro
Kapoor, Shubham
Ansari, Abdul Fatir
Stella, Lorenzo
Shen, Huibin
Senetaire, Hugo
Turkmen, Caner
Shchur, Oleksandr
Maddix, Danielle C.
Bohlke-Schneider, Michael
Wang, Yuyang
Rangapuram, Syama Sundar
author_facet Arango, Sebastian Pineda
Mercado, Pedro
Kapoor, Shubham
Ansari, Abdul Fatir
Stella, Lorenzo
Shen, Huibin
Senetaire, Hugo
Turkmen, Caner
Shchur, Oleksandr
Maddix, Danielle C.
Bohlke-Schneider, Michael
Wang, Yuyang
Rangapuram, Syama Sundar
contents Covariates provide valuable information on external factors that influence time series and are critical in many real-world time series forecasting tasks. For example, in retail, covariates may indicate promotions or peak dates such as holiday seasons that heavily influence demand forecasts. Recent advances in pretraining large language model architectures for time series forecasting have led to highly accurate forecasters. However, the majority of these models do not readily use covariates as they are often specific to a certain task or domain. This paper introduces a new method to incorporate covariates into pretrained time series forecasting models. Our proposed approach incorporates covariate information into pretrained forecasting models through modular blocks that inject past and future covariate information, without necessarily modifying the pretrained model in consideration. In order to evaluate our approach, we introduce a benchmark composed of 32 different synthetic datasets with varying dynamics to evaluate the effectivity of forecasting models with covariates. Extensive evaluations on both synthetic and real datasets show that our approach effectively incorporates covariate information into pretrained models, outperforming existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12107
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables
Arango, Sebastian Pineda
Mercado, Pedro
Kapoor, Shubham
Ansari, Abdul Fatir
Stella, Lorenzo
Shen, Huibin
Senetaire, Hugo
Turkmen, Caner
Shchur, Oleksandr
Maddix, Danielle C.
Bohlke-Schneider, Michael
Wang, Yuyang
Rangapuram, Syama Sundar
Machine Learning
Artificial Intelligence
Covariates provide valuable information on external factors that influence time series and are critical in many real-world time series forecasting tasks. For example, in retail, covariates may indicate promotions or peak dates such as holiday seasons that heavily influence demand forecasts. Recent advances in pretraining large language model architectures for time series forecasting have led to highly accurate forecasters. However, the majority of these models do not readily use covariates as they are often specific to a certain task or domain. This paper introduces a new method to incorporate covariates into pretrained time series forecasting models. Our proposed approach incorporates covariate information into pretrained forecasting models through modular blocks that inject past and future covariate information, without necessarily modifying the pretrained model in consideration. In order to evaluate our approach, we introduce a benchmark composed of 32 different synthetic datasets with varying dynamics to evaluate the effectivity of forecasting models with covariates. Extensive evaluations on both synthetic and real datasets show that our approach effectively incorporates covariate information into pretrained models, outperforming existing baselines.
title ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.12107