Efficient Extraction of Target Users for Package Promotion in Big Social Networks
Bibliographic Data
| ID | 22108922 |
|---|---|
| Authors | Lo-Yao Yeh (0000-0002-9764-0455, National Chi Nan University), Hsien-Chu Wu (0000-0002-4313-9585, National Chin-Yi University of Technology) |
| Year | 2020 |
| Volume | 7 |
| Issue | 5 |
| Pages | 1111-1122 |
| Publication date | 2020-10-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | IEEE Transactions on Computational Social Systems (JOURNAL) |
| Journal identifiers | ISSN: 2329-924X • E-ISSN: 2373-7476 |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) (PUBLISHER) |
| DOI | 10.1109/tcss.2020.3007754 |
| OpenAlex | W3043180219 |
| Language | EN |
| Citations received | 1 |
| References cited | 52 |
Package promotion (or product bundling and bundle promotion) is widely adopted as an effective marketing strategy to increase sales, but the social tightness of the users significantly influences their willingness to purchase certain products. However, addressing these two factors simultaneously is not a trivial task because it is critical to properly choose a set of socially tight target users to encourage them to buy the products together (social tightness factor), and the selected users should have high preference for the package of products (preference factor). To address the aforementioned challenges, in this article, we study the research problem of promoting a package of products to a set of closely related friends. We formulate a new research problem, named package-oriented group identification (PGI), which can obtain a set of t socially tight users (i.e., inducing more than k edges) who have the maximum preference for a package of items. We prove that the proposed PGI problem is NP-hard, and we develop a polynomial-time algorithm named incremental solution construction with redundancy and infeasibility avoidance for PGI (ISCP) that can effectively and efficiently obtain a good solution to the PGI problem. We compare the performance of ISCP with four other baselines on a large-scale product copurchasing data set with more than 500 k products and 1.7 M copurchasing relationships. The results show that our proposed ISCP algorithm outperforms the other baselines in terms of solution quality and efficiency
Mathematical optimization · Preference · Auction Theory and Applications · Computer Science · Consumer Market Behavior and Pricing · Digital Marketing and Social Media · Mathematics
| Citations per year | 1 |
|---|---|
| Citation span | 2025 - 2025 (1) |
| Highly cited | No |