# Daily Emergency Call Volume Forecasting using Univariate and Multivariate TimeGPT

DevFeed: [Daily Emergency Call Volume Forecasting using Univariate and Multivariate TimeGPT](<https://devfeed.tech/articles/daily-emergency-call-volume-forecasting-using-univariate-and-multivariate-timegpt-125419.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11613>)

Author: Feriel Fass, Djemel Ziou

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Data science and engineering](<https://devfeed.tech/topics/data-science-and-engineering.md>), [Hyperparameter optimization](<https://devfeed.tech/topics/hyperparameter-optimization.md>), [mlp](<https://devfeed.tech/topics/mlp.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [application](<https://devfeed.tech/tags/application.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [best](<https://devfeed.tech/tags/best.md>), [better](<https://devfeed.tech/tags/better.md>), [boosting](<https://devfeed.tech/tags/boosting.md>), [call](<https://devfeed.tech/tags/call.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [daily](<https://devfeed.tech/tags/daily.md>), [data](<https://devfeed.tech/tags/data.md>), [emergency](<https://devfeed.tech/tags/emergency.md>), [error](<https://devfeed.tech/tags/error.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [grid](<https://devfeed.tech/tags/grid.md>), [large](<https://devfeed.tech/tags/large.md>), [long-short-term-memory](<https://devfeed.tech/tags/long-short-term-memory.md>), [volume](<https://devfeed.tech/tags/volume.md>)

## AI overview

On 2,101 daily emergency call observations, TimeGPT did not outperform simpler established methods overall: SARIMAX performed best in the univariate setting, while Poisson regression and Negative Binomial regression performed best in the multivariate setting. The study compared one-step-ahead and seven-day forecasts, adding temporal, weather, demographic, and socioeconomic variables in multivariate models. It used chronological training, validation, and test splits, with validation-based grid search and early stopping when applicable. The findings suggest large-scale pretraining did not guarantee better accuracy for this application; the excerpt does not provide metric values or results for each forecast horizon.

## Source excerpt

arXiv:2611.11613v1 Announce Type: new Abstract: This study investigates the potential of TimeGPT, a pretrained foundation model for timeseries, for forecasting daily emergency call volumes. Real-world emergency call data, comprising 2,101 daily observations, are used to evaluate both univariate and multivariate forecasting settings under one-step-ahead and seven-day multi-step-ahead scenarios. The multivariate forecasting incorporates temporal, meteorological, demographic, and socioeconomic variables. A chronological training, validation, and test split is adopted to prevent information leakage, while hyperparameters are selected using the validation set through grid search and early stopping when applicable. Forecasting performance is evaluated using multiple error metrics. Its forecasting performance is compared with several established forecasting approaches, including Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SARIMAX), Poisson regression (PR), Negative Binomial regression (NBR), Extreme Gradient Boosting (XGBoost), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM). The results show that SARIMAX achieves the best overall performance in the univariate setting. In the multivariate setting, NBR and PR provide best performance. These findings indicate that the large-scale pretraining of TimeGPT do not necessarily translate into superior forecasting accuracy for emergency call volumes. Frugal methods trained solely on the available data remain better for this application.