Apparatus for fraud detection rule optimization
AssigneeBottomline Technologies, Inc.
InventorsAvital Serfaty, Shahar Cohen, Yulia Mayer, Dalit Amitai
Life of this patent
Estimating the term…
Abstract
An improved method and apparatus for determining if a financial transaction is fraudulent is described. The apparatus in one embodiment collects transactions off of a rail using promiscuous listening techniques. The method uses linear programming algorithms to tune the rules used for making the determination. The tuning first simulates using historical data and then creates a matrix of the rules that are processed through the linear programming algorithm to solve for the variables in the rules. With the updated rules, a second simulation is performed to view the improvement in the performance. The updated rules are then used to evaluate the transactions for fraud.
Claims20
A p-monitor comprising a central processing unit and non-transitory computer readable memory programmed to:
- create a matrix of each rule in a draft rule set for each historical transaction in historical data stored in a data store;
- solve the matrix for each rule score using linear programming;
- copy said rule scores into a model rule set;
- monitor a rail for a new transaction;
- apply data from the new transaction to the model rule set;
- produce a new transaction score from the data and the model rule set;
- and
- indicate that the new transaction is fraudulent if the new transaction score exceeds a threshold.
An apparatus comprising:
- a p-monitor;
- a rail transceiver, the p-monitor connected to the rail transceiver, the rail transceiver configured to monitor a rail for a new transaction and provide the new transaction to the p-monitor;
- a data store connected to the p-monitor, the data stored containing historical data and a draft rule set;
- the p-monitor is configured to:
- create a matrix of each rule in the draft rule set for each historical transaction in the historical data;
- solve the matrix for each rule score using linear programing, said rule scores used to form a model rule set;
- apply data from the new transaction to the model rule set to produce a new transaction score;
- and
- if the new transaction score exceeds a threshold, indicate that the new transaction is fraudulent.
An apparatus comprising:
- a p-monitor;
- a rail transceiver, the p-monitor connected to the rail transceiver, the rail transceiver configured to monitor a rail for a new transaction and provide the new transaction to the p-monitor;
- a data store connected to the p-monitor, the data store containing historical data and a draft rule set;
- the p-monitor including:
- a means for creating a matrix of each rule in the draft rule set for each historical transaction in the historical data;
- a means for solving the matrix for each rule score using linear programming, said rule scores used to form a model rule set;
- a means for producing a new transaction score by applying data from the new transaction to the model rule set;
- and
- if the new transaction score exceeds a threshold, indicate that the new transaction is fraudulent.
Dependencies are inferred from the claim text.