LOF: identifying density-based local outliers
SIGMOD '00 Proceedings of the 2000 ACM SIGMOD international conference on Management of data
IDA '01 Proceedings of the 4th International Conference on Advances in Intelligent Data Analysis
On-Line Unsupervised Outlier Detection Using Finite Mixtures with Discounting Learning Algorithms
Data Mining and Knowledge Discovery
Using relational knowledge discovery to prevent securities fraud
Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
ICDMW '10 Proceedings of the 2010 IEEE International Conference on Data Mining Workshops
Mining medical specialist billing patterns for health service management
AusDM '08 Proceedings of the 7th Australasian Data Mining Conference - Volume 87
Discovering inappropriate billings with local density based outlier detection method
AusDM '09 Proceedings of the Eighth Australasian Data Mining Conference - Volume 101
Hi-index | 0.00 |
In this paper, we present a novel approach to re-estimate the risk level of prescribers and consumers (doctors and patients) that were previously evaluated by various independent Risk Analysis Systems (RAS). This is achieved by taking into consideration social network structure between prescribers and consumers. A mathematical model, called Asymmetrical Rating Exchange Model (AREM) is proposed to describe the mutual influences between prescribers and consumers from a social network perspective and based on this model an algorithm is derived to re-estimate the suspicion level of each entity in the community considering both the pre-evaluated rating and the network structure. Additionally, by comparing the pre-evaluated rating and the re-estimated risk level, under-rated entities can be identified and further assessed. Experimental results are also presented, showing that the proposed approach can effectively detect the entities that have strong connections to high risk entities, but previously been rated low suspicious by independent Risk Analysis Systems (RAS).