Saved in:
Bibliographic Details
Main Authors: Arab, Issar, Benitez, Rodrigo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.03395
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909478638583808
author Arab, Issar
Benitez, Rodrigo
author_facet Arab, Issar
Benitez, Rodrigo
contents Time series forecasting is essential for operational intelligence in the hospitality industry, and particularly challenging in large-scale, distributed systems. This study evaluates the performance of statistical, machine learning (ML), deep learning, and foundation models in forecasting hourly sales over a 14-day horizon using real-world data from a network of thousands of restaurants across Germany. The forecasting solution includes features such as weather conditions, calendar events, and time-of-day patterns. Results demonstrate the strong performance of ML-based meta-models and highlight the emerging potential of foundation models like Chronos and TimesFM, which deliver competitive performance with minimal feature engineering, leveraging only the pre-trained model (zero-shot inference). Additionally, a hybrid PySpark-Pandas approach proves to be a robust solution for achieving horizontal scalability in large-scale deployments.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmarking Time Series Forecasting Models: From Statistical Techniques to Foundation Models in Real-World Applications
Arab, Issar
Benitez, Rodrigo
Machine Learning
Artificial Intelligence
Time series forecasting is essential for operational intelligence in the hospitality industry, and particularly challenging in large-scale, distributed systems. This study evaluates the performance of statistical, machine learning (ML), deep learning, and foundation models in forecasting hourly sales over a 14-day horizon using real-world data from a network of thousands of restaurants across Germany. The forecasting solution includes features such as weather conditions, calendar events, and time-of-day patterns. Results demonstrate the strong performance of ML-based meta-models and highlight the emerging potential of foundation models like Chronos and TimesFM, which deliver competitive performance with minimal feature engineering, leveraging only the pre-trained model (zero-shot inference). Additionally, a hybrid PySpark-Pandas approach proves to be a robust solution for achieving horizontal scalability in large-scale deployments.
title Benchmarking Time Series Forecasting Models: From Statistical Techniques to Foundation Models in Real-World Applications
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.03395