Weekly sales forecasting using time series decomposition with irregular seasonality: A case study of Sony TV sales in the United States
PLOS One · 03.11.2026 · 21 (11) · e0344222
DOI: 10.1371/journal.pone.0344222 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 03.11.2026. Verfasst von Arthur Matsuo Yamashita Rios de Sousa und 11 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, Institute of Science Tokyo, Yokohama, Japan. Hauptthemen laut MEDLINE: Seasons, Commerce, Television. Die Arbeit nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sony.
Abstract (Originalsprache)
In the practice of sales forecasting, alongside high accuracy, simplicity and interpretability are desirable qualities in a predictive model. Here, we use time series decomposition to construct a simple and interpretable forecasting method for weekly sales, taking as a case study the total weekly sales of Sony TV units in the United States. The main challenge is to properly address irregular seasonality arising from the way a year is divided into weeks and from floating holidays and events. As a solution, we propose the concept of ‘analogous weeks’, a general framework for grouping weeks that are similar according to some criteria, which encodes seasonality and already accounts for calendar effects. By incorporating this notion into the time series decomposition and forecasting, we achieved yearly average percentage errors of less than 10% for the 1-week-ahead forecast and less than 15% for forecast horizons of up to 26 weeks, accuracy levels comparable to or better than those of other established seasonal models, namely Prophet and SARIMAX, particularly at longer forecast horizons.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computing, Institute of Science Tokyo, Yokohama, Japan.
- Department of Data Science, Yokohama City University, Yokohama, Japan.
- Institute of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan.
- School of Engineering, Institute of Science Tokyo, Yokohama, Japan.
ORCID-Profile: Arthur Matsuo Yamashita Rios de Sousa, Yixuan Y Zheng
Förderung
- Sony
Zitieren
APA
Yamashita Rios de Sousa, A. M., Ando, D., Ozaki, J., Shida, Y., Wu, Q., Zheng, Y. Y., Zhong, Z., Maskawa, R., Jiang, J. J., Nagayama, K., Takayasu, H., & Takayasu, M. (2026). Weekly sales forecasting using time series decomposition with irregular seasonality: A case study of Sony TV sales in the United States. PLOS One, 21(11), e0344222. https://doi.org/10.1371/journal.pone.0344222
Vancouver
Yamashita Rios de Sousa AM, Ando D, Ozaki J, Shida Y, Wu Q, Zheng YY, et al. Weekly sales forecasting using time series decomposition with irregular seasonality: A case study of Sony TV sales in the United States. PLOS One. 2026;21(11):e0344222. doi:10.1371/journal.pone.0344222
BibTeX
@article{YamashitaRiosdeSousa2026,
author = {Yamashita Rios de Sousa, Arthur Matsuo and Ando, Daisuke and Ozaki, Junichi and Shida, Yohei and Wu, Qianyun and Zheng, Yixuan Y and Zhong, Zhihua and Maskawa, Rie and Jiang, Jiwei J and Nagayama, Kay and Takayasu, Hideki and Takayasu, Misako},
title = {Weekly sales forecasting using time series decomposition with irregular seasonality: A case study of Sony TV sales in the United States},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0344222},
doi = {10.1371/journal.pone.0344222}
}
EUVIMED