Systems and methods for assigning attribution weights to nodes

A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, causes the processing device to perform operations comprising:

• configuring a plurality of processors, wherein each of the plurality of processors is coupled to a respective cache that provides data locality;
• receiving, via an application program interface (API), a plurality of data records, wherein each data record comprises a plurality of attribute values associated with a transaction;
• grouping the plurality of data records into two or more clusters, wherein each cluster is associated with a respective set of attribute values, and wherein no two clusters share a same set of attribute values;
• identifying a respective set of rules for each cluster of the two or more clusters;
• loading the data records and the respective set of rules for each cluster into a respective cache;
• and
• analyzing, in parallel with a plurality of program threads that execute on a respective processor associated with the respective cache and without accessing an external memory, such that the cache provides data locality for the data records using the respective set of rules, wherein the analyzing includes:
• determining a rule associated with each data record of the cluster based on a subset of attribute values in the data record that match a particular rule of the respective set of rules;
• and
• determining one or more transaction-specific parameters based on the rule.

A system comprising:

• a memory with instructions stored thereon;
• and
• a processing device, coupled to the memory, the processing device configured to access the memory and execute the instructions, wherein the instructions cause the processing device to perform operations including:
• configuring a plurality of processors, wherein each of the plurality of processors is coupled to a respective cache that provides data locality;
• receiving, via an application program interface (API), a plurality of data records, wherein each data record comprises a plurality of attribute values associated with a transaction;
• grouping the plurality of data records into two or more clusters, wherein each cluster is associated with a respective set of attribute values, and wherein no two clusters share a same set of attribute values;
• identifying a respective set of rules for each cluster of the two or more clusters;
• loading the data records and the respective set of rules for each cluster into a respective cache;
• and
• analyzing, in parallel with a plurality of program threads that execute on a respective processor associated with the respective cache and without accessing an external memory, such that the cache provides data locality for the data records using the respective set of rules, wherein the analyzing includes:
• determining a rule associated with each data record of the cluster based on a subset of attribute values in the data record that match a particular rule of the respective set of rules;
• and
• determining one or more transaction-specific parameters based on the rule.