Bibliographic Details
| Title: |
Key quality characteristic selection incorporating customer attention under imbalanced data for popular products. |
| Authors: |
Shi, Liangxing, Zhang, Jiaqi, He, Yingdong, He, Zhen |
| Source: |
International Journal of Production Research; Mar2026, Vol. 64 Issue 6, p2311-2330, 20p |
| Subject Terms: |
MULTI-objective optimization, CONSUMER preferences, FEATURE selection, METAHEURISTIC algorithms, QUALITY assurance, RECOMMENDER systems, COMMERCIAL products, DATA quality |
| Abstract: |
Effective key quality characteristic (KQC) selection is essential for follow-up quality improvement. Customers' demands for different product QCs affect product popularity. However, little research has integrated customer attention into KQC selection under imbalanced data in e-commerce, which can lead to a follow-up product with good quality but no popularity. This study, therefore, investigated KQC selection incorporating customer attention in the scenario of imbalanced data for popular products. First, KQC selection incorporating customer attention was defined as a multi-objective problem, aiming to minimise the percentage of selected QCs and maximise the importance of QCs, as well as cumulative attention to selected QCs. A collaborative filtering algorithm-based method was applied to extract customer attention from historical data when filtering key QCs. Second, an adaptive hybrid whale optimisation algorithm (AHWOA) was proposed to solve KQC selection. Here, simulated annealing was incorporated into the WOA agent search, and an adaptive convergence-acceleration mechanism and a fast non-dominated sorting algorithm with an improved crowding-distance measure were integrated into WOA. Third, the proposed AHWOA was evaluated on five datasets from the UCI repository, and the results show AHWOA's advantages over five existing benchmark algorithms. [ABSTRACT FROM AUTHOR] |
|
Copyright of International Journal of Production Research is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Complementary Index |
Full Text Finder 
Nájsť tento článok vo Web of Science