| CPC G06Q 20/102 (2013.01) [G06Q 20/123 (2013.01); G06Q 20/14 (2013.01); G06Q 20/401 (2013.01)] | 20 Claims |

|
1. A computer-implemented method comprising:
determining a combination of a plurality of values of a plurality of attributes represented by reference data associated with a plurality of payment transactions by training a machine learning model based on the reference data, wherein the reference data contains an association between (i) respective values of the plurality of attributes and (ii) the plurality of payment transactions having a first result of a plurality of possible results, and wherein the combination of the plurality of values is correlated with having the first result;
selecting at least a first payment transaction subset from the plurality of payment transactions such that each respective payment transaction of the first payment transaction subset is associated with the combination of the plurality of values;
determining, based on a first reference data subset of the reference data, at least a first measure indicative of a first rate at which payment transactions of the first payment transaction subset have the first result during a first time period represented by the first reference data subset, wherein the first reference data subset corresponds to the first payment transaction subset;
determining, based on production data corresponding to one or more payment transactions associated with the combination of the plurality of values, at least a second measure indicative of a second rate at which the one or more payment transactions have the first result during a second time period represented by the production data; and
generating, based on a comparison of the first measure to the second measure, an indication that the second rate differs from the first rate by more than a predefined threshold amount.
|