EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sales forecasting for retail stores using hybrid neural networks and sales-affecting variables

Saad Mansur, Kashif Sattar, Seyed Ebrahim Hosseini, Shahbaz Pervez iD, Iftikhar Ahmad iD, Kashif Saleem iD, Ahmed Zohier Elhendi

PeerJ Computer Science · 11.09.2025 · 11 · e3058

DOI: 10.7717/peerj-cs.3058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 11.09.2025. Verfasst von Saad Mansur und 6 weiteren Autor:innen. Beteiligte Einrichtung: Whitecliffe, Auckland, New Zealand. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Saud University, Riyadh, Saudi Arabia, Researchers Supporting Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate sales forecasting is vital for balancing demand and supply and enhancing profitability in the retail sector. Deep learning (DL) models have shown promise in this area; however, most either handle temporal or spatial patterns in isolation. Moreover, many studies rely on synthetic datasets or omit critical contextual variables, reducing real-world accuracy. This study proposes a hybrid convolutional neural network (CNN)-long short-term memory (LSTM) model for retail sales forecasting using real-world data enhanced with environmental and demographic variables in term of holidays, salary days, protests, and weather conditions. CNNs capture spatial patterns, while LSTMs model temporal dependencies, making the hybrid architecture well-suited for multivariate forecasting tasks. Our model demonstrates a significant improvement in predictive performance, achieving a mean absolute percentage error (MAPE) of 4.16%, outperforming traditional and standalone neural models. By incorporating external factors, the proposed approach enables more reliable forecasting and supports informed decision-making in retail operations.

Schlagwörter

Stichwörter der Autor:innen

CNNDeep learningHybrid neural networkLSTMMutivariate datasetRetail storeSales forecasting

Autor:innen und Institutionen

  • Whitecliffe, Auckland, New Zealand.
  • University of Arid Agriculture Rawalpindi, Rawalpindi, Panjab, Pakistan.
  • Faculty of Computing and Information Technology, King Abdul Aziz University, Jeddah, Saudi Arabia.
  • Center of Excellence in Information Assurance, DSR, King Saud University, Riyadh, Saudi Arabia.
  • Science Technology and Innovation Department, King Saud University, Riyadh, Saudi Arabia.

ORCID-Profile: Shahbaz Pervez, Iftikhar Ahmad, Kashif Saleem

Förderung

  • King Saud University, Riyadh, Saudi Arabia
  • Researchers Supporting Project

Zitieren

APA

Mansur, S., Sattar, K., Hosseini, S. E., Pervez, S., Ahmad, I., Saleem, K., & Zohier Elhendi, A. (2025). Sales forecasting for retail stores using hybrid neural networks and sales-affecting variables. PeerJ Computer Science, 11, e3058. https://doi.org/10.7717/peerj-cs.3058

Vancouver

Mansur S, Sattar K, Hosseini SE, Pervez S, Ahmad I, Saleem K, et al. Sales forecasting for retail stores using hybrid neural networks and sales-affecting variables. PeerJ Computer Science. 2025;11:e3058. doi:10.7717/peerj-cs.3058

BibTeX
@article{Mansur2025,
  author = {Mansur, Saad and Sattar, Kashif and Hosseini, Seyed Ebrahim and Pervez, Shahbaz and Ahmad, Iftikhar and Saleem, Kashif and Zohier Elhendi, Ahmed},
  title = {Sales forecasting for retail stores using hybrid neural networks and sales-affecting variables},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e3058},
  doi = {10.7717/peerj-cs.3058}
}
Kostenlos starten →