发明名称 |
Fraud detection and analysis |
摘要 |
Systems and methods generate a risk score for an account event. The systems and methods automatically generate a causal model corresponding to a user, wherein the model estimates components of the causal model using event parameters of a previous event undertaken by the user in an account of the user. The systems and methods predict expected behavior of the user during a next event in the account using the causal model. Predicting the expected behavior of the user includes generating expected event parameters of the next event. The systems and methods use a predictive fraud model to generate fraud event parameters. Generation of the fraud event parameters assumes a fraudster is conducting the next event, wherein the fraudster is any person other than the user. The systems and methods generate a risk score of the next event to indicate the relative likelihood the future event is performed by the user. |
申请公布号 |
US8862526(B2) |
申请公布日期 |
2014.10.14 |
申请号 |
US201213632834 |
申请日期 |
2012.10.01 |
申请人 |
Guardian Analytics, Inc. |
发明人 |
Miltonberger Tom |
分类号 |
G06N3/02;G06F7/04;G06Q40/02;G06Q10/06;G06Q50/26;G06Q10/10;G06N5/02;G06Q20/40 |
主分类号 |
G06N3/02 |
代理机构 |
IPR Law Group, PC |
代理人 |
IPR Law Group, PC |
主权项 |
1. A method comprising:
generating probabilistic relationships between event parameters of a previous event and derived parameters of an owner of an account; automatically generating a user model including the probabilistic relationships; dynamically updating the user model using event parameters of a future event; and predicting during the future event with use of the user model whether the owner or a fraudster is perpetuating the future event, wherein an event includes an action taken in the account during access of the account. |
地址 |
Mountain View CA US |