Generalized means match foundation models for predicting emergency calls

Means vs. Foundation Models for Emergency Call Forecasting

Machine Learning

Summary

Predicting how many emergency calls will happen each day helps services prepare better. This study found that simple math tools called generalized means can forecast daily emergency calls just as well as a complex AI model called TimeGPT. For very short-term predictions, the simple methods sometimes did even better. Over longer periods, the AI model performed slightly better, but the difference was not statistically significant. This means simple, less resource-heavy methods can be useful alternatives to big AI models for this task.

What this means in practice

  • For emergency response planners: Use simple generalized mean methods to forecast daily emergency call volumes efficiently for up to a week ahead.
  • For energy management teams: Reduce computing energy in forecasting emergency calls by opting for generalized means instead of large AI models without losing accuracy.

Authors

Feriel Fass, Djemel Ziou, Marie-Flavie Auclair-Fortier

Abstract

This study investigates whether generalized means can achieve forecasting performance comparable to that of TimeGPT for daily emergency call volume prediction. Specifically, two families of generalized means, the Hölder means (HM) and the Lehmer means (LM), are evaluated against fine-tuned TimeGPT across forecasting horizons ranging from one to seven days. Forecasting performance is assessed on a real-world emergency call dataset using multiple error metrics, and Diebold-Mariano test. Experimental results show that HM and LM achieve nearly identical predictive performance across all forecasting horizons. For short-term forecasting, both generalized means outperform TimeGPT, with reductions of mean absolute error (MAE) approximately 1.24\% and 2.48\% at horizons of one and three days, respectively. Conversely, TimeGPT achieves a lower error at the seven-day horizon, with an descresing of MAE by 1.98\%. However, Diebold-Mariano tests reveal no statistically significant differences between the methods at the evaluated horizons. These findings suggest that generalized means can provide competitive forecasting performance compared with a energyvore foundation model.