Forecasting product sales using text mining: a case study in new energy vehicle

Yi Ding, Peng Wu (), Jie Zhao and Ligang Zhou
Additional contact information
Yi Ding: Anhui University
Peng Wu: Anhui University
Jie Zhao: Anhui University
Ligang Zhou: Anhui University

Electronic Commerce Research, 2025, vol. 25, issue 1, No 17, 495-527

Abstract: Abstract This study aims to improve the prediction accuracy of product sales by developing an online review-driven combination forecasting model. The proposed model includes two parts: online reviews and the forecasting model. For online reviews, the sentiment value concerning different product attributes is defined from the sentiment score and the sentiment tendency based on prospect theory. Furthermore, the Mallat pyramid algorithm is used to mitigate the impact of reviews with nonstandard expressions, malicious reviews and spam on the sentiment value of online reviews. A combination forecasting model composed of a backpropagation neural network (BPNN), recurrent neural network (RNN) and long short-term memory (LSTM) neural network is constructed. Taking the sales of BYD-Tang as a case study, some statistical evaluation indicators and the Diebold-Mariano (DM) test indicate the superior performance of our proposed online review-driven combination forecasting model in prediction accuracy.

Keywords: E-commerce; Sales forecasting; Online reviews; Combination forecasting (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10660-023-09701-9 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:elcore:v:25:y:2025:i:1:d:10.1007_s10660-023-09701-9

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10660

DOI: 10.1007/s10660-023-09701-9

Access Statistics for this article

Electronic Commerce Research is currently edited by James Westland

More articles in Electronic Commerce Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().