Quantum Computing in Community Detection for Anti-Fraud Applications
Fraud detection within transaction data is crucial for maintaining financial security, especially in the era of big data. This paper introduces a novel fraud detection method that utilizes quantum computing to implement community detection in transaction networks. We model transaction data as an und...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/26/12/1026 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850240905022275584 |
|---|---|
| author | Yanbo (Justin) Wang Xuan Yang Chao Ju Yue Zhang Jun Zhang Qi Xu Yiduo Wang Xinkai Gao Xiaofeng Cao Yin Ma Jie Wu |
| author_facet | Yanbo (Justin) Wang Xuan Yang Chao Ju Yue Zhang Jun Zhang Qi Xu Yiduo Wang Xinkai Gao Xiaofeng Cao Yin Ma Jie Wu |
| author_sort | Yanbo (Justin) Wang |
| collection | DOAJ |
| description | Fraud detection within transaction data is crucial for maintaining financial security, especially in the era of big data. This paper introduces a novel fraud detection method that utilizes quantum computing to implement community detection in transaction networks. We model transaction data as an undirected graph, where nodes represent accounts and edges indicate transactions between them. A modularity function is defined to measure the community structure of the graph. By optimizing this function through the Quadratic Unconstrained Binary Optimization (QUBO) model, we identify the optimal community structure, which is then used to assess the fraud risk within each community. Using a Coherent Ising Machine (CIM) to solve the QUBO model, we successfully divide 308 nodes into four communities. We find that the CIM computes faster than the classical Louvain and simulated annealing (SA) algorithms. Moreover, the CIM achieves better community structure than Louvain and SA as quantified by the modularity function. The structure also unambiguously identifies a high-risk community, which contains almost 70% of all the fraudulent accounts, demonstrating the practical utility of the method for banks’ anti-fraud business. |
| format | Article |
| id | doaj-art-72d8065589384eed9c59df40d4140e84 |
| institution | OA Journals |
| issn | 1099-4300 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj-art-72d8065589384eed9c59df40d4140e842025-08-20T02:00:45ZengMDPI AGEntropy1099-43002024-11-012612102610.3390/e26121026Quantum Computing in Community Detection for Anti-Fraud ApplicationsYanbo (Justin) Wang0Xuan Yang1Chao Ju2Yue Zhang3Jun Zhang4Qi Xu5Yiduo Wang6Xinkai Gao7Xiaofeng Cao8Yin Ma9Jie Wu10Longying Zhida (Beijing) Technology Co., Ltd., Beijing 100020, ChinaLongying Zhida (Beijing) Technology Co., Ltd., Beijing 100020, ChinaBeijing QBoson Quantum Technology Co., Ltd., Beijing 100015, ChinaLongying Zhida (Beijing) Technology Co., Ltd., Beijing 100020, ChinaLongying Zhida (Beijing) Technology Co., Ltd., Beijing 100020, ChinaLongying Zhida (Beijing) Technology Co., Ltd., Beijing 100020, ChinaLongying Zhida (Beijing) Technology Co., Ltd., Beijing 100020, ChinaLongying Zhida (Beijing) Technology Co., Ltd., Beijing 100020, ChinaLongying Zhida (Beijing) Technology Co., Ltd., Beijing 100020, ChinaBeijing QBoson Quantum Technology Co., Ltd., Beijing 100015, ChinaBeijing QBoson Quantum Technology Co., Ltd., Beijing 100015, ChinaFraud detection within transaction data is crucial for maintaining financial security, especially in the era of big data. This paper introduces a novel fraud detection method that utilizes quantum computing to implement community detection in transaction networks. We model transaction data as an undirected graph, where nodes represent accounts and edges indicate transactions between them. A modularity function is defined to measure the community structure of the graph. By optimizing this function through the Quadratic Unconstrained Binary Optimization (QUBO) model, we identify the optimal community structure, which is then used to assess the fraud risk within each community. Using a Coherent Ising Machine (CIM) to solve the QUBO model, we successfully divide 308 nodes into four communities. We find that the CIM computes faster than the classical Louvain and simulated annealing (SA) algorithms. Moreover, the CIM achieves better community structure than Louvain and SA as quantified by the modularity function. The structure also unambiguously identifies a high-risk community, which contains almost 70% of all the fraudulent accounts, demonstrating the practical utility of the method for banks’ anti-fraud business.https://www.mdpi.com/1099-4300/26/12/1026coherent ising machine (CIM)quantum computingcommunity detectionquadratic unconstrained binary optimization (QUBO)Louvainsimulated annealing |
| spellingShingle | Yanbo (Justin) Wang Xuan Yang Chao Ju Yue Zhang Jun Zhang Qi Xu Yiduo Wang Xinkai Gao Xiaofeng Cao Yin Ma Jie Wu Quantum Computing in Community Detection for Anti-Fraud Applications Entropy coherent ising machine (CIM) quantum computing community detection quadratic unconstrained binary optimization (QUBO) Louvain simulated annealing |
| title | Quantum Computing in Community Detection for Anti-Fraud Applications |
| title_full | Quantum Computing in Community Detection for Anti-Fraud Applications |
| title_fullStr | Quantum Computing in Community Detection for Anti-Fraud Applications |
| title_full_unstemmed | Quantum Computing in Community Detection for Anti-Fraud Applications |
| title_short | Quantum Computing in Community Detection for Anti-Fraud Applications |
| title_sort | quantum computing in community detection for anti fraud applications |
| topic | coherent ising machine (CIM) quantum computing community detection quadratic unconstrained binary optimization (QUBO) Louvain simulated annealing |
| url | https://www.mdpi.com/1099-4300/26/12/1026 |
| work_keys_str_mv | AT yanbojustinwang quantumcomputingincommunitydetectionforantifraudapplications AT xuanyang quantumcomputingincommunitydetectionforantifraudapplications AT chaoju quantumcomputingincommunitydetectionforantifraudapplications AT yuezhang quantumcomputingincommunitydetectionforantifraudapplications AT junzhang quantumcomputingincommunitydetectionforantifraudapplications AT qixu quantumcomputingincommunitydetectionforantifraudapplications AT yiduowang quantumcomputingincommunitydetectionforantifraudapplications AT xinkaigao quantumcomputingincommunitydetectionforantifraudapplications AT xiaofengcao quantumcomputingincommunitydetectionforantifraudapplications AT yinma quantumcomputingincommunitydetectionforantifraudapplications AT jiewu quantumcomputingincommunitydetectionforantifraudapplications |