Automated fraud monitoring and trigger-system for detecting unusual patterns associated with fraudulent activity, and corresponding method thereof

1. An automated real-time fraud monitoring and detection system triggered by unusual and/or suspicious activities within a data processing workflow based on pattern recognition and matching, the automated real-time fraud monitoring and detection system comprising:

processing circuitry configured to

capture, in a first data structure, a set of claim parameters and data, underwriting parameters and data, and application parameters and data, the data comprising digitized multimedia-data, and the claim and underwriting parameters and data being extracted from associated risk-transfer underwriting and claim data sources and/or capturing systems, the digitized multimedia-data comprising data extracted from microblogging services and/or social networking services by the system from social network data comprising recognized social formation data, social media data and/or social relationship data and/or behavioral data and/or interaction data, based on relationship disclosures from the application parameters and data captured at a time of application,

generate synthetic forms of social formation data and social formation metadata comprising at least the social media data and/or behavioral data and/or social relationship data and/or interaction data,

detect and/or recognize data associatable with one or more claim applicants and/or beneficiaries and/or agents and assign the detected data to network nodes or network edges, the social data and metadata being stored in corresponding data records of a second data structure, a network node representing a claim applicant or beneficiary or agent and a network edge representing a link between a claim applicant and beneficiary or a claim applicant and an agent or a beneficiary and an agent, chains of the nodes interconnected by the network edges are formed as a network structure by a network engine based on the data of the first data structure and the second data structure, the network being formed using a network analysis structure, the network nodes being interconnected by edges linking each node of the network structure with at least one other node of the network structure, and

identify, flag, and monitor fraudulent networks using connectivity and degree metrics to trigger on network structures indicative of fraudulent and/or suspicious activities, the chains of the nodes being formed by node triggers of the system identifying groups of nodes having motive characteristics to abuse the system and/or benefit from a claim process, wherein the node triggers trigger the data of the first data structure and/or the second data structure based on trigger values indicating motive characteristics to abuse the system and/or benefit from the claim process, the trigger values of the node triggers being dynamically adapted by a machine-learning-based process based on dynamically captured data of the first data structure and/or the second data structure.

2. The automated real-time fraud monitoring and detection system according to claim 1 , wherein the network nodes and edges of the network structure are varied by the system reflecting different attributes to provide qualitative assessment of the network.

3. The automated real-time fraud monitoring and detection system according to claim 1 , wherein the network analysis structure used is centrality and/or in-degree and/or out-degree and/or density.

4. The automated real-time fraud monitoring and detection system according to claim 1 , wherein the processing circuitry is configured to perform a pattern-recognition process based on machine-learning or artificial intelligence, wherein identified network structures indicative of fraudulent and/or suspicious activities are used in a learning phase of the pattern-recognition process, and wherein in an operation phase of the pattern-recognition process the identification of fraudulent network structures is performed by the pattern-recognition process using the network structure as input parameters.

5. The automated real-time fraud monitoring and detection system according to claim 4 , wherein the pattern-recognition process further performs:

determining a plurality of the nodes and edges based on the data of the first and second data structure, the nodes being interconnected by edges to form different network structures,

determining one of more operational modus variables of each set of claim parameters and data, the operational modus variables indicative of motives to abuse the system and/or benefit from a claim process,

determining a match between the one or more operational modus variables and a claim in the sets of open claims,

generating a list of suspected fraudulent claims that comprises each matched claim,

implementing one or more machine learning algorithms to learn a fraud signature pattern in the list of suspected fraudulent claims, and

grouping the set of open claims data based on the fraud identifying and flagging fraudulent applicants and/or beneficiaries and/or agents.

6. The automated real-time fraud monitoring and detection system according to claim 1 , wherein when one fraudulent node is identified in a selected network structure, all the other nodes are also flagged to be processed further for fraudulent activities.

7. The automated real-time fraud monitoring and detection system according to claim 1 , wherein the network structure is formed by connecting attributes of groups of people intending to benefit from a claim process based on trigger characteristics comprising common names and/or address similarities and/or insured identities and/or beneficiary identities.

8. The automated real-time fraud monitoring and detection system according to claim 1 , wherein the processing circuitry is configured to detect any node which is beneficiary for at least n different nodes representing applicants, and, when the networks structures are formed, flag the network structures when more than m unique last names are detected.

9. The automated real-time fraud monitoring and detection system according to claim 1 , wherein the processing circuitry is configured to use a statistical analysis process to determine outlier nodes representing agents, where detected outliner nodes are flagged as agents engaging in potentially fraudulent activity.

10. The automated real-time fraud monitoring and detection system according to claim 9 , wherein the statistical analysis process to determine outlier nodes is performed on underwriting decisions across a portfolio.

11. The automated real-time fraud monitoring and detection system according to claim 8 , wherein nodes representing agents are flagged when identified as statistical outliers on a risk adjusted basis.

12. The automated real-time fraud monitoring and detection system according to claim 9 , wherein the processing circuitry is configured to trigger more thorough diligence on submitted applications, when a node representing an agent is flagged by processing circuitry.

13. The automated real-time fraud monitoring and detection system according to claim 9 , wherein the statistical analysis process is performed by the processing circuitry across several metrics.

14. The automated real-time fraud monitoring and detection system according to claim 13 , wherein the several metrics comprise at least approvals and/or declines and/or self-disclosure.

15. The automated real-time fraud monitoring and detection system according to claim 1 , further comprising:

a data-transmission network comprising secured communication channels linked on one side to client devices each comprising a graphical user interface for inputting claim data and on an other side to an automated claim capturing data source of the system for capturing claim data, which is digitized multimedia-data, transmitted from a client device, of the client devices, over a secure communication channel, of the secure communication channels, wherein the risk-transfer underwriting and claim data sources and/or capturing systems are an integrated part of the system.

16. The automated real-time fraud monitoring and detection system according to claim 15 , wherein the transmitted multimedia-data comprise at least digital text and/or image data automatically recognized by the automated claim data capturing data source, wherein recognized parts of the transmitted multimedia-data are assigned to the set of claim parameters and data of the first data structure as extracted and recognized claim parameters and data.

17. The automated real-time fraud monitoring and detection system according to claim 16 , wherein the transmitted multimedia-data comprises microblogging services, which comprise at least online broadcast medium Twitter and/or Tumblr and/or FriendFeed and/or Plurk and/or Jaiku and/or identi.ca and/or Sina Weibo and/or Tencent Weibo.

18. The automated real-time fraud monitoring and detection system according to claim 17 , wherein the microblogging services comprise, besides web-based interfaces, alternative publishing entries including text messaging and/or instant messaging and/or electronic mail and/or digital audio and/or digital video.

19. The automated real-time fraud monitoring and detection system according to claim 16 , wherein the transmitted multimedia-data comprises social networking services comprising at least Facebook and/or MySpace and/or LinkedIn and/or Diaspora and/or JudgIt and/or Yahoo Pulse and/or Google Buzz and/or Google+ and/or XING.

20. The automated real-time fraud monitoring and detection system according to claim 19 , wherein the social networking services further comprise micro-blogging feature implemented as status updates features.

21. The automated real-time fraud monitoring and detection system according to claim 1 , further comprising:

a data-transmission network comprising secured communication channels linked on one side to client devices each comprising a graphical user interface for inputting underwriting data and on an other side to an automated underwriting capturing data source for capturing underwriting data, which comprise digitize multimedia-data, transmitted form a client device, of the client devices, over a secure communication channel, of the secure communication channels, wherein the risk-transfer underwriting and claim data sources and/or capturing systems are an integrated part of the system.

22. The automated real-time fraud monitoring and detection system according to claim 1 , further comprising:

one or more first risk transfer systems to provide a first risk transfer based on first risk transfer parameters from a plurality of risk-exposed individuals to the first risk transfer system, wherein the claim applicants are a part of the risk-exposed individuals, wherein the first risk transfer system comprises a plurality of payment transfer modules configured to receive and store first payment parameters associated with risk transfer of risk exposures of the risk-exposed individuals for pooling of their risks.

23. The automated real-time fraud monitoring and detection system according to claim 22 , further comprising:

a second risk transfer system to provide a second risk transfer based on second risk transfer parameters from one or more of the first risk transfer systems to the second risk transfer system, wherein the second risk transfer system comprises second payment transfer modules configured to receive and store second payment parameters for pooling of the risks of the first risk transfer systems associated with risk exposures transferred to the first risk transfer systems.

24. The automated real-time fraud monitoring and detection system according to claim 23 , wherein the second risk transfer parameters and correlated second payment transfer parameters are generated by a machine learning-based control circuit and transmitted to the second risk transfer system, wherein occurred loss is at least partly covered by the second risk transfer system based on the second risk transfer parameters and correlated second payment transfer parameters.

25. The automated real-time fraud monitoring and detection system according to claim 24 , wherein the first and second risk transfer parameters and the correlated first and second payment transfer parameters are dynamically adapted and/or optimized by the machine learning-based control circuit based on captured risk-related individual data and based on the pooled risks of the first risk transfer systems.

26. The automated real-time fraud monitoring and detection system according to claim 25 , wherein the first and second risk transfer parameters and the correlated first and second payment transfer parameters are dynamically adapted and/or optimized by the machine learning-based control circuit, further based upon measuring cost impact of the measured and monitored fraudulent activities.

27. The automated real-time fraud monitoring and detection system according to claim 1 , wherein the processing circuitry is configured to generate synthetic forms of the social formation data and social formation metadata being based on relationship disclosure data captured at the time of application comprising at least the social media data and/or behavioral data and/or social relationship data and/or interaction data at least partially captured from the application data and parameters and/or microblogging services and/or social networking services.

28. The automated real-time fraud monitoring and detection system according to claim 27 , wherein the social formation data and social formation metadata are based on relationship disclosures at the time of application captured from the application data and parameters, wherein each applicant situate beneficiaries for a respective application, and each of the beneficiaries having individual applications and further beneficiaries, an applicant to beneficiary relationship being a basis of formation of the network structure.