Nirmaljit Singh
Ikvinderpal Singh
- Research Scholar Department of Computer Science and Engineering, Sant Baba Bhag Singh University, Jalandhar Punjab India
- Assistant Professor PG Department of Computer Science and Applications, Trai Shatabdi Guru Gobind Singh Khalsa College, Amritsar Punjab India
Abstract
Link prediction is a challenging task in recommender systems, as it requires the ability to accurately predict future links between users and items. In this study, we propose a novel hybrid link prediction algorithm for e-commerce recommender systems that combines the common neighbor and resource allocation methods. The common neighbor method is a straightforward and intuitive algorithm that calculates the number of shared neighbors between two nodes. The intuition is that if two nodes have many common neighbors, they are more likely to be linked in the future. The resource allocation method is a more sophisticated algorithm that weights the common neighbors based on their importance. The intuition is that if two nodes have common neighbors that are themselves well-connected, then the two nodes are more likely to be linked. Our proposed hybrid algorithm combines the strengths of the common neighbor and resource allocation methods. We first calculate the common neighbor score between each pair of users and items. Afterward, the common neighbor score is adjusted by considering the significance or importance of the shared neighbors. The importance of a common neighbor is calculated using a resource allocation algorithm.
Keywords: Resource allocation algorithm, novel hybrid link prediction algorithm, recommender systems, ROC curve, AUC curve, sophisticated algorithm
[This article belongs to International Journal of Data Structure Studies(ijdss)]
References
1. Liben-Nowell D, Kleinberg J. The link prediction problem for social networks. In Proceedings of the 12th international conference on Information and knowledge management. 2003 Nov 3; 556–559.
2. Wang P, Xu B, Wu Y, Zhou X. Link prediction in social networks: the state-of-the-art. arXiv preprint arXiv:1411.5118. 2014 Nov 19.
3. Newman ME. The structure of scientific collaboration networks. Proc Natl Acad Sci. 2001 Jan 16; 98(2): 404–9.
4. 6Zhang Q, Tong T, Wu S. Hybrid link prediction via model averaging. Physica A: Statistical Mechanics and Its Applications. 2020 Oct 15; 556: 124772.
5. Jaccard P. Étude comparative de la distribution florale dans une portion des Alpes et des Jura. Bull Soc Vaudoise Sci Nat. 1901; 37(142): 547–79.
6. Fortunato S. Community detection in graphs. Phys Rep. 2010 Feb 1; 486(3–5): 75–174.
7. Li Y, Kou G, Li G, Wang H. Multi-attribute group decision making with opinion dynamics based on social trust network. Inf Fusion. 2021 Nov 1; 75: 102–15.
8.
Su Z, Zheng X, Ai J, Shang L, Shen Y. Link prediction in recommender systems with confidence measures. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2019 Aug 1; 29(8): 083133.
9. Ma C, Zhang WE, Guo M, Wang H, Sheng QZ. Multi-document summarization via deep learning techniques: A survey. ACM Comput Surv. 2022 Dec 3; 55(5): 1–37.
10. Lakshmi TJ, Bhavani SD. Link prediction approach to recommender systems. arXiv preprint arXiv:2102.09185. 2021 Feb 18.
11. Zhou T. Link prediction in complex networks: A survey. Physica A: Statistical Mechanics and its Applications. 2011; 390(6): 1150–70.
12. Lei C, Ruan J. A novel link prediction algorithm for reconstructing protein–protein interaction networks by topological similarity. Bioinformatics. 2013 Feb 1; 29(3): 355–64.
13. Xie F, Chen Z, Shang J, Feng X, Li J. A link prediction approach for item recommendation with complex number. Knowl-Based Syst. 2015 Jun 1; 81: 148–58.
| Volume | 01 |
| Issue | 01 |
| Received | July 19, 2023 |
| Accepted | July 24, 2023 |
| Published | September 4, 2023 |