EUVIMEDEUVIMED entdecken
Crossref

Utilizing Online Reviews and Search Traffic Data for Game Product Demand Forecasting via an Improved Bass Model

Weiyu Zhao, Zhuxuan Xia, Yicheng Feng, Jinfeng Wang, Yanan Guo, Ningtao Wang, Haoyu Wang

IEEE Transactions on Engineering Management · 2026 · 73 · 4163-4175

DOI: 10.1109/tem.2026.3710916 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Engineering Management, 2026. Verfasst von Weiyu Zhao und 6 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The game industry has evolved into a core component of digital economy infrastructure, integrating export growth, employment creation, and technological innovation, thereby occupying a strategic position in national competitiveness. However, demand for game consoles has declined steadily, making accurate demand forecasting essential to improving industrial performance and resource allocation recently. Previous studies primarily relied on multiple linear regression and other approaches based on single endogenous variables, such as historical sales, which fail to capture the uncertain, dynamic, and interactive nature of console demand. To enhance the accuracy of demand prediction for game console products, this article utilizes multisource data, including online review data and search traffic data. An improved Bass demand prediction model is proposed and subsequently applied to predict demand for three categories of game consoles: Xbox, PlayStation 5, and Nintendo Switch. The results indicate that: First, incorporating variables extracted from online reviews, such as sentiment polarity, consumer expectations, and defect perception, into the demand model refines the imitation coefficient and enhances the model's responsiveness to consumer satisfaction. Second, adjusting the innovation coefficient based on search traffic data of products and complementary goods allows the model to better capture the impact of market popularity and external information diffusion on demand dynamics. Finally, the optimal parameters were estimated using the nonlinear least squares method and validated using R2, weighted absolute percentage error, and PE metrics. The results demonstrate that the improved model outperforms in both goodness of fit and forecasting accuracy, confirming its applicability to high volatility and intensely interactive product markets.

Förderung

  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • National Key Research and Development Program of China

Zitieren

APA

Zhao, W., Xia, Z., Feng, Y., Wang, J., Guo, Y., Wang, N., & Wang, H. (2026). Utilizing Online Reviews and Search Traffic Data for Game Product Demand Forecasting via an Improved Bass Model. IEEE Transactions on Engineering Management, 73, 4163-4175. https://doi.org/10.1109/tem.2026.3710916

Vancouver

Zhao W, Xia Z, Feng Y, Wang J, Guo Y, Wang N, et al. Utilizing Online Reviews and Search Traffic Data for Game Product Demand Forecasting via an Improved Bass Model. IEEE Transactions on Engineering Management. 2026;73:4163-4175. doi:10.1109/tem.2026.3710916

BibTeX
@article{Zhao2026,
  author = {Zhao, Weiyu and Xia, Zhuxuan and Feng, Yicheng and Wang, Jinfeng and Guo, Yanan and Wang, Ningtao and Wang, Haoyu},
  title = {Utilizing Online Reviews and Search Traffic Data for Game Product Demand Forecasting via an Improved Bass Model},
  journal = {IEEE Transactions on Engineering Management},
  year = {2026},
  volume = {73},
  pages = {4163--4175},
  doi = {10.1109/tem.2026.3710916}
}
Kostenlos starten →