Skip to content
DraconiticResearch
Search Sources API
186,086 studies31 sourcesUpdated 23 min ago
Peer-reviewedCC BY 4.0PLOS One

Weekly sales forecasting using time series decomposition with irregular seasonality: A case study of Sony TV sales in the United States

  • Arthur Matsuo Yamashita Rios de Sousa1
  • Daisuke Ando2
  • Junichi Ozaki3
  • Yohei Shida4
  • Qianyun Wu
  • Yixuan Y. Zheng
  • Zhihua Zhong
  • Rie Maskawa
  • Jiwei J. Jiang
  • Kay Nagayama
  • Hideki Takayasu
  • Misako Takayasu
4 affiliations
  1. 1School of Computing, Institute of Science Tokyo, Yokohama, Japan
  2. 2Department of Data Science, Yokohama City University, Yokohama, Japan
  3. 3Institute of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan
  4. 4School of Engineering, Institute of Science Tokyo, Yokohama, Japan
Open at sourceDOICite

Abstract

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.

Related

  1. Forecasting Weekly Influenza Detections in South Africa Using SARIMA and LSTM Models
    Ebelechukwu Ajuka, Ebenezer Esenogho, Cameron Modisane
    Journal of Information Systems and InformaticsPeer-reviewedCC BYFull textGeneral mathematicsDOAJ
  2. PAR2COX: Survival-Informed Tensor Decomposition for Phenotyping and Risk Prediction from Irregular Longitudinal Data
    Mariafrancesca Patalano, Elif Konyar, Kamran Paynabar
    arXivPreprintarXiv licenceFull textStatisticsarXiv
  3. A Combinatorial Benders Decomposition Framework for Two-Dimensional Irregular Bin Packing Problems with Convex Polygons
    Jianming Wang, Zhouwang Yang
    arXivPreprintarXiv licenceFull textOptimisation & controlarXiv
  4. The H-IAR Model for Irregular Multispectral Time Series. Quaternion Formulation, Mapping of Resilience Indicators, and Exploratory Identification of Forest Edges
    Bruno Goncalves C. Filho, Angelo Calil BianchiBruno Goncalves C. Filho, Aluisio Pinheiro
    arXivPreprintCC0Full textStatisticsarXiv
  5. Hankel-Koopman Finite-Horizon Energy Decomposition of Coupled Experimental Data: A Three-Phase Data-Driven Twin Forecasting Framework
    Diana A. Bistrian, Marcel Topor
    arXivPreprintCC BY 4.0Full textNumerical analysis & scientific computingarXiv

Cite

BibTeXRIS
BibTeX
@article{sousa2026weekly,
  title = {{Weekly sales forecasting using time series decomposition with irregular seasonality: A case study of Sony TV sales in the United States}},
  author = {Arthur Matsuo Yamashita Rios de Sousa and Daisuke Ando and Junichi Ozaki and Yohei Shida and Qianyun Wu and Yixuan Y. Zheng and Zhihua Zhong and Rie Maskawa and Jiwei J. Jiang and Kay Nagayama and Hideki Takayasu and Misako Takayasu},
  journal = {PLOS One},
  year = {2026},
  month = nov,
  doi = {10.1371/journal.pone.0344222},
  url = {https://doi.org/10.1371/journal.pone.0344222},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Weekly sales forecasting using time series decomposition with irregular seasonality: A case study of Sony TV sales in the United States
AU  - Arthur Matsuo Yamashita Rios de Sousa
AU  - Daisuke Ando
AU  - Junichi Ozaki
AU  - Yohei Shida
AU  - Qianyun Wu
AU  - Yixuan Y. Zheng
AU  - Zhihua Zhong
AU  - Rie Maskawa
AU  - Jiwei J. Jiang
AU  - Kay Nagayama
AU  - Hideki Takayasu
AU  - Misako Takayasu
PY  - 2026
DA  - 2026/11/03
JO  - PLOS One
DO  - 10.1371/journal.pone.0344222
UR  - https://doi.org/10.1371/journal.pone.0344222
AB  - 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.
SN  - 1932-6203
ER  -