Determining a temporary transaction limit

A method, comprising:

• receiving a transaction request message, wherein the transaction request message includes a total transaction cost associated with a requested transaction and identifying information associated with a user, wherein the user is associated with a plurality of historical transaction costs;
• dynamically determining a predetermined limit associated with the user, wherein dynamically determining the predetermined limit comprises:
• ranking, by size, the plurality of historical transaction costs associated with the user;
• determining an outlier condition;
• determining one or more historical transaction costs associated with the user that meet the outlier condition from the plurality of historical transaction costs associated with the user;
• and
• determining the predetermined limit associated with the user based at least in part on a maximum value from the plurality of historical transaction costs associated with the user excluding the one or more historical transaction costs associated with the user that meet the outlier condition;
• determining the total transaction cost is greater than the predetermined limit;
• obtaining a plurality of clustered classifications that is generated from historical data of a plurality of users based at least in part on clustering at least a portion of the historical data of the plurality of users;
• selecting, using one or more processors, a clustered classification corresponding to the user from the plurality of clustered classifications based at least in part on the plurality of historical transaction costs associated with the user, including:
• applying a user score derived based on the plurality of historical transaction costs associated with the user to determine the selected clustered classification;
• determining a dynamic quota corresponding to the clustered classification for the user using a predetermined mapping rule, wherein a first clustered classification is related by the predetermined mapping rule to a first dynamic quota and a second clustered classification is related by the predetermined mapping rule to a second dynamic quota, wherein the first dynamic quota is different from the second dynamic quota;
• determining to approve the transaction request message based at least in part on determining that the total transaction cost is less than a temporary transaction limit, wherein the temporary transaction limit comprises a combination of the predetermined limit and the dynamic quota;
• and
• in response to the determination to approve the transaction request message, completing the requested transaction.

A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

• receiving a transaction request message, wherein the transaction request message includes a total transaction cost associated with a requested transaction and identifying information associated with a user, wherein the user is associated with a plurality of historical transaction costs;
• dynamically determining a predetermined limit associated with the user, wherein dynamically determining the predetermined limit comprises:
• ranking, by size, the plurality of historical transaction costs associated with the user;
• determining an outlier condition;
• determining one or more historical transaction costs associated with the user that meet the outlier condition from the plurality of historical transaction costs associated with the user;
• and
• determining the predetermined limit associated with the user based at least in part on a maximum value from the plurality of historical transaction costs associated with the user excluding the one or more historical transaction costs associated with the user that meet the outlier condition;
• determining the total transaction cost is greater than the predetermined limit;
• obtaining a plurality of clustered classifications that is generated from historical data of a plurality of users based at least in part on clustering at least a portion of the historical data of the plurality of users;
• selecting a clustered classification corresponding to the user from the plurality of clustered classifications based at least in part on the plurality of historical transaction costs associated with the user, including:
• applying a user score derived based on the plurality of historical transaction costs associated with the user to determine the selected clustered classification;
• determining a dynamic quota corresponding to the clustered classification for the user using a predetermined mapping rule, wherein a first clustered classification is related by the predetermined mapping rule to a first dynamic quota and a second clustered classification is related by the predetermined mapping rule to a second dynamic quota, wherein the first dynamic quota is different from the second dynamic quota;
• determining to approve the transaction request message based at least in part on determining that the total transaction cost is less than a temporary transaction limit, wherein the temporary transaction limit comprises a combination of the predetermined limit and the dynamic quota;
• and
• in response to the determination to approve the transaction request message, completing the requested transaction.