Fraud detection and analysis

A method comprising:

• automatically generating a first model using account event parameters of a previous account event performed by a user in an account, via an online banking system, wherein the first model includes distributions of the account event parameters;
• receiving observed account event parameters of a next account event in the online banking system
• wherein the previous account event and the next account event are at least one of:
• an online event, an offline event or a multiple-channel event;
• generating a first probability using the first model,
• wherein the first probability corresponds to the user conducting the next account event in the online banking system;
• generating a second probability using a second model,
• wherein the second probability corresponds to a fraudster conducting the next account event in the online banking system, wherein the fraudster is a person other than the user;
• and
• using the first probability and the second probability, generating a likelihood the next account event in the online banking system is performed by the user versus the fraudster;
• wherein generating the first model includes generating statistical relationships between the account event parameters and derived parameters corresponding to the account, and
• wherein the derived parameters include one or more of a geographic area from which a device is initiating the future account event to the online banking system, a location of the device, an identification of the device, and an electronic service provider of the device.

A system comprising at least one processor configured for:

• generating a first model using account event parameters of at least one account event in an account of a user via an online banking system,
• wherein the at least one account event in the account is at least one of:
• an online event, an offline event or a multiple-channel event;
• using the first model, predicting expected behavior of the user during a future account event in the account, in the online banking system;
• generating fraud event parameters using a second model;
• and
• generating with the first model and the second model a probability the future account event is performed by the user, in the online banking system;
• wherein generating the first model includes generating statistical relationships between the account event parameters and derived parameters corresponding to the account, and
• wherein the derived parameters include one or more of a geographic area from which a device is initiating the future event in the online banking system, a location of the device, an identification of the device, and an electronic service provider of the device.

A system comprising at least one processor configured for:

• automatically generating a first model using account event parameters of a previous account event performed by a user in an account, via an online banking system,
• wherein the first model includes distributions of the event parameters;
• receiving observed event parameters of a next account event in the online banking system;
• wherein the previous account event and the next account event are at least one of:
• an online event, an offline event or a multiple-channel event;
• generating a first probability using the first model,
• wherein the first probability corresponds to the user conducting the next account event in the online banking system;
• generating a second probability using a second model,
• wherein the second probability corresponds to a fraudster conducting the next account event, in the online banking system,
• wherein the fraudster is a person other than the user;
• and
• using the first probability and the second probability, generating a likelihood the next account event in the online banking system, is performed by the user versus the fraudster;
• wherein generating the first model includes generating statistical relationships between the event parameters and derived parameters corresponding to the account, and
• wherein the derived parameters include one or more of a geographic area from which a device is initiating the next account event, in the online banking system, a location of the device, an identification of the device, and an electronic service provider of the device.

A computer program product comprising a non-transitory computer usable medium having computer readable program code embodied therein, the computer readable program code comprising instructions for:

• generating a first model using event parameters of at least one account event in an account of a user via an online banking system,
• wherein the at least one account event in the account is at least one of:
• an online event,
• an offline event or a multiple-channel event;
• using the first model, predicting expected behavior of the user during a future account event in the account in the online banking system;
• generating fraud event parameters using a second model;
• and
• generating with the first model and the second model a probability the future account event is performed by the user in the online banking system;
• wherein generating the first model includes generating statistical relationships between the event parameters and derived parameters corresponding to the account, and
• wherein the derived parameters include one or more of a geographic area from which a device is initiating the future account event, in the online banking system a location of the device, an identification of the device, and an electronic service provider of the device.

A computer program product comprising a non-transitory computer usable medium having computer readable program code embodied therein, the computer readable program code comprising instructions for:

• automatically generating a first model using event parameters of a previous account event performed by a user in an account, via an online banking system,
• wherein the first model includes distributions of the event parameters;
• receiving observed event parameters of a next account event in the online banking system,
• wherein the previous account event and the next account event are at least one of:
• an online event, an offline event or a multiple-channel event;
• generating a first probability using the first model,
• wherein the first probability corresponds to the user conducting the next account event in the online banking system;
• generating a second probability using a second model,
• wherein the second probability corresponds to a fraudster conducting the next account event, in the online banking system, and
• wherein the fraudster is a person other than the user;
• and
• using the first probability and the second probability, generating a likelihood the next account event is performed by the user versus the fraudster in the online banking system;
• wherein generating the first model includes generating statistical relationships between the event parameters and derived parameters corresponding to the account, and
• wherein the derived parameters include one or more of a geographic area from which a device is initiating the next account event, in the online banking system, a location of the device, an identification of the device, and an electronic service provider of the device.