Design of e-commerce product price prediction model based on generative adversarial network with adaptive weight adjustment

Abstract E-commerce platforms have amassed extensive transaction data, which serves as a valuable source for price prediction. However, the diversity of commodities poses challenges such as data imbalance, model overfitting, and underfitting. To address these issues, this paper presents an improved...

Full description

Saved in:
Bibliographic Details
Main Authors: Abuduaini Abudureheman, Yan Zhao, Aishanjiang Nilupaer
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10767-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333412518690816
author Abuduaini Abudureheman
Yan Zhao
Aishanjiang Nilupaer
author_facet Abuduaini Abudureheman
Yan Zhao
Aishanjiang Nilupaer
author_sort Abuduaini Abudureheman
collection DOAJ
description Abstract E-commerce platforms have amassed extensive transaction data, which serves as a valuable source for price prediction. However, the diversity of commodities poses challenges such as data imbalance, model overfitting, and underfitting. To address these issues, this paper presents an improved generative adversarial network model that integrates the strengths of Conditional Generative Adversarial Nets and the Wasserstein Generative Adversarial Network. By introducing Wasserstein scatter and removing Lipschitz constraints, we propose the CWGAN model to mitigate data imbalance and enhance the quality of generated samples. Furthermore, we incorporate Adaptive Weight Adjustment (AWA) and a differential evolution strategy, resulting in the Adaptive Weight Adjustment-Conditional Wasserstein Generative Adversarial Network (AWA-CWGAN) algorithm. This algorithm employs a neighborhood learning strategy to update the optimal individuals within subpopulations, thereby reinforcing the influence of elite individuals during population evolution. Additionally, dynamic weight adjustment based on sparsity is implemented to increase genetic diversity within the population. Experimental results demonstrate that the AWA-CWGAN algorithm achieves complete convergence with only 16–25% of the global evolutionary generations required by the standard differential evolutionary algorithm or the hybrid frog-leaping algorithm. Moreover, the AWA-CWGAN algorithm surpasses baseline methods in accuracy (88.8%), precision (88.81%), recall (89.255%), and F1 score (87.95%). These results indicate that the proposed approach significantly enhances the accuracy of e-commerce product price predictions, providing robust decision-making support for merchants.
format Article
id doaj-art-980ba1d2ea4341a28af768d5f64ad23a
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-980ba1d2ea4341a28af768d5f64ad23a2025-08-20T03:45:52ZengNature PortfolioScientific Reports2045-23222025-07-0115111210.1038/s41598-025-10767-8Design of e-commerce product price prediction model based on generative adversarial network with adaptive weight adjustmentAbuduaini Abudureheman0Yan Zhao1Aishanjiang Nilupaer2School of Economics, Guangdong University of Finance and EconomicsSchool of Public Finance and Taxation of GDUFE, Guangdong University of Finance and EconomicsSchool of Information Management, Xinjiang University of Finance and EconomicsAbstract E-commerce platforms have amassed extensive transaction data, which serves as a valuable source for price prediction. However, the diversity of commodities poses challenges such as data imbalance, model overfitting, and underfitting. To address these issues, this paper presents an improved generative adversarial network model that integrates the strengths of Conditional Generative Adversarial Nets and the Wasserstein Generative Adversarial Network. By introducing Wasserstein scatter and removing Lipschitz constraints, we propose the CWGAN model to mitigate data imbalance and enhance the quality of generated samples. Furthermore, we incorporate Adaptive Weight Adjustment (AWA) and a differential evolution strategy, resulting in the Adaptive Weight Adjustment-Conditional Wasserstein Generative Adversarial Network (AWA-CWGAN) algorithm. This algorithm employs a neighborhood learning strategy to update the optimal individuals within subpopulations, thereby reinforcing the influence of elite individuals during population evolution. Additionally, dynamic weight adjustment based on sparsity is implemented to increase genetic diversity within the population. Experimental results demonstrate that the AWA-CWGAN algorithm achieves complete convergence with only 16–25% of the global evolutionary generations required by the standard differential evolutionary algorithm or the hybrid frog-leaping algorithm. Moreover, the AWA-CWGAN algorithm surpasses baseline methods in accuracy (88.8%), precision (88.81%), recall (89.255%), and F1 score (87.95%). These results indicate that the proposed approach significantly enhances the accuracy of e-commerce product price predictions, providing robust decision-making support for merchants.https://doi.org/10.1038/s41598-025-10767-8Generative adversarial networksAdaptive weight adjustmentDifferential evolutionPrice prediction
spellingShingle Abuduaini Abudureheman
Yan Zhao
Aishanjiang Nilupaer
Design of e-commerce product price prediction model based on generative adversarial network with adaptive weight adjustment
Scientific Reports
Generative adversarial networks
Adaptive weight adjustment
Differential evolution
Price prediction
title Design of e-commerce product price prediction model based on generative adversarial network with adaptive weight adjustment
title_full Design of e-commerce product price prediction model based on generative adversarial network with adaptive weight adjustment
title_fullStr Design of e-commerce product price prediction model based on generative adversarial network with adaptive weight adjustment
title_full_unstemmed Design of e-commerce product price prediction model based on generative adversarial network with adaptive weight adjustment
title_short Design of e-commerce product price prediction model based on generative adversarial network with adaptive weight adjustment
title_sort design of e commerce product price prediction model based on generative adversarial network with adaptive weight adjustment
topic Generative adversarial networks
Adaptive weight adjustment
Differential evolution
Price prediction
url https://doi.org/10.1038/s41598-025-10767-8
work_keys_str_mv AT abuduainiabudureheman designofecommerceproductpricepredictionmodelbasedongenerativeadversarialnetworkwithadaptiveweightadjustment
AT yanzhao designofecommerceproductpricepredictionmodelbasedongenerativeadversarialnetworkwithadaptiveweightadjustment
AT aishanjiangnilupaer designofecommerceproductpricepredictionmodelbasedongenerativeadversarialnetworkwithadaptiveweightadjustment