A comparison of Holts-Winter and Artificial Neural Network approach in forecasting: A case study for tent manufacturing industry

Abstract

The imperative of accurate forecasting spans diverse industrial sectors, notably impacting the tent manufacturing industry. This study embarks on a rigorous examination and development of novel forecasting models, specifically tailored for this sector. We introduce and juxtapose two distinct approaches: the Holt-Winters method and Artificial Neural Networks (ANN). Our analysis is grounded in a case study of a tent manufacturing company, delving into the dynamics of demand variation, particularly under seasonal influences. Through meticulous comparison, we demonstrate the efficacy of the ANN model, highlighting its superior accuracy in forecasting, especially for the Elite and Party Canopy tent models, albeit with a noted prediction error of 15% for the Vista tents. The paper also explores the broader supply chain context of the tent industry, examining influential factors affecting commercial tent sales and identifying key supply chain players. Our findings underscore the nuanced capabilities of ANN in capturing intricate demand patterns, offering a promising direction for refining forecasting practices in the tent manufacturing industry.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 28 citations exist upstream.