Prioritizing data clusters with customizable scoring strategies
View Patent ↗Techniques are disclosed for prioritizing a plurality of clusters. Prioritizing clusters may generally include identifying a scoring strategy for prioritizing the plurality of clusters. Each cluster is generated from a seed and stores a collection of data retrieved using the seed. For each cluster, elements of the collection of data stored by the cluster are evaluated according to the scoring strategy and a score is assigned to the cluster based on the evaluation. The clusters may be ranked according to the respective scores assigned to the plurality of clusters. The collection of data stored by each cluster may include financial data evaluated by the scoring strategy for a risk of fraud. The score assigned to each cluster may correspond to an amount at risk.
1. A computer-implemented method for prioritizing a plurality of data entity clusters, the method comprising:
communicating with one or more electronic data stores storing a plurality of data entities and respective data entity attributes, the one or more electronic data stores in communication with one or more hardware computer processors, the one or more hardware computer processors configured with specific computer executable instructions, and the plurality of data entities related to financial data and including at least one of:
an account data entity,
a transaction data entity,
a customer data entity, or
a phone number data entity;
generating, by the one or more hardware computer processors, a plurality of data entity clusters that each store a collection of related data entities, each of the data entity clusters generated by:
identifying and adding a seed data entity to the data entity cluster; and
determining and adding to the data entity cluster, based on a cluster strategy configured to identify related data entities for detection of possible fraudulent financial activity, one or more additional data entities related to the seed data entity;
identifying, by the one or more hardware computer processors, a scoring strategy for prioritizing the plurality of data entity clusters;
for each data entity cluster:
evaluating, by the one or more hardware computer processors and based on the scoring strategy, the data entity cluster; and
assigning, by the one or more hardware computer processors and based on the evaluation, a score to the data entity cluster; and
ranking the plurality of data entity clusters according to the respective assigned scores,
wherein the plurality of ranked data entity clusters are useable by an analyst to determine various data entities related to each other and to possible fraudulent financial activity.
2. The method of claim 1 , wherein the collection of related data entities stored by each data entity cluster is evaluated according to the scoring strategy to determine a risk of financial fraud.
3. The method of claim 1 , wherein the score assigned to each data entity cluster corresponds to an amount at risk.
4. The method of claim 1 , wherein assigning a score to the data entity cluster comprises:
determining a plurality of base scores for the data entity cluster;
determining, based on the plurality of base scores, an overall score for the data entity cluster; and
assigning the overall score to the data entity cluster.
5. The method of claim 1 further comprising:
presenting, on an electronic display viewable by a user, a listing and/or summary of one or more of the plurality of data entity clusters according to the ranking.
6. The method of claim 5 , wherein the listing and/or summary presents the seed data entity associated with each of the one or more or the plurality of clusters.
7. The method of claim 1 further comprising:
identifying a second scoring strategy for prioritizing the plurality of data entity clusters;
for each data entity cluster:
evaluating one or more attributes of the collection of related data entities stored by the data entity cluster according to the second scoring strategy; and
assigning a second score to the data entity cluster;
re-ranking the plurality of data entity clusters according to the respective assigned second scores; and
presenting, on an electronic display viewable by a user, a listing and/or summary of one or more of the plurality of data entity clusters according to the re-ranking.
8. A non-transitory computer-readable storage medium storing computer-executable instructions that, when executed by a computer system, configure the computer system to perform operations comprising:
communicating with one or more electronic data stores storing a plurality of data entities and respective data entity attributes, the plurality of data entities related to financial data and including at least one of:
an account data entity,
a transaction data entity,
a customer data entity, or
a phone number data entity;
generating a plurality of data entity clusters that each store a collection of related data entities, each of the data entity clusters generated by:
identifying and adding a seed data entity to the data entity cluster; and
determining and adding to the data entity cluster, based on a cluster strategy configured to identify related data entities for detection of possible fraudulent financial activity, one or more additional data entities related to the seed data entity;
identifying a scoring strategy for prioritizing the plurality of data entity clusters;
for each data entity cluster:
evaluating, based on the scoring strategy, the data entity cluster; and
assigning, based on the evaluation, a score to the data entity cluster; and
ranking the plurality of data entity clusters according to the respective assigned scores,
wherein the plurality of ranked data entity clusters are useable by an analyst to determine various data entities related to each other and to possible fraudulent financial activity.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the collection of related data entities stored by each data entity cluster is evaluated according to the scoring strategy to determine a risk of financial fraud.
10. The non-transitory computer-readable storage medium of claim 8 , wherein the score assigned to each data entity cluster corresponds to an amount at risk.
11. The non-transitory computer-readable storage medium of claim 8 , wherein assigning a score to the data entity cluster comprises:
determining a plurality of base scores for the data entity cluster;
determining, based on the plurality of base scores, an overall score for the data entity cluster; and
assigning the overall score to the data entity cluster.
12. The non-transitory computer-readable storage medium of claim 8 , wherein the computer-executable instructions configure the computer system to perform further operations comprising:
presenting, on an electronic display viewable by a user, a listing and/or summary of one or more of the plurality of data entity clusters according to the ranking.
13. The non-transitory computer-readable storage medium of claim 12 , wherein the listing and/or summary presents the seed data entity associated with each of the one or more or the plurality of clusters.
14. The non-transitory computer-readable storage medium of claim 8 , wherein the computer-executable instructions configure the computer system to perform further operations comprising:
identifying a second scoring strategy for prioritizing the plurality of data entity clusters;
for each data entity cluster:
evaluating one or more attributes of the collection of related data entities stored by the data entity cluster according to the second scoring strategy; and
assigning a second score to the data entity cluster;
re-ranking the plurality of data entity clusters according to the respective assigned second scores; and
presenting, on an electronic display viewable by a user, a listing and/or summary of one or more of the plurality of data entity clusters according to the re-ranking.
15. A computer system comprising:
one or more non-transitory computer readable storage devices configured to store one or more software programs; and
one or more hardware computer processors in communication with the one or more non-transitory computer readable storage devices and configured to execute the one or more software programs in order to cause the computer system to:
communicate with one or more electronic data stores storing a plurality of data entities and respective data entity attributes, the plurality of data entities related to financial data and including at least one of:
an account data entity,
a transaction data entity,
a customer data entity, or
a phone number data entity;
generate, by the one or more hardware computer processors, a plurality of data entity clusters that each store a collection of related data entities, each of the data entity clusters generated by:
identifying and adding a seed data entity to the data entity cluster; and
determining and adding to the data entity cluster, based on a cluster strategy configured to identify related data entities for detection of possible fraudulent financial activity, one or more additional data entities related to the seed data entity;
identify, by the one or more hardware computer processors, a scoring strategy for prioritizing the plurality of data entity clusters;
for each data entity cluster:
evaluate, by the one or more hardware computer processors and based on the scoring strategy, the data entity cluster; and
assign, by the one or more hardware computer processors and based on the evaluation, a score to the data entity cluster; and
rank the plurality of data entity clusters according to the respective assigned scores,
wherein the plurality of ranked data entity clusters are useable by an analyst to determine various data entities related to each other and to possible fraudulent financial activity.
16. The computer system of claim 15 , wherein the collection of related data entities stored by each data entity cluster is evaluated according to the scoring strategy to determine a risk of financial fraud.
17. The computer system of claim 15 , wherein the score assigned to each data entity cluster corresponds to an amount at risk.
18. The computer system of claim 15 , wherein assigning a score to the data entity cluster comprises:
determining a plurality of base scores for the data entity cluster;
determining, based on the plurality of base scores, an overall score for the data entity cluster; and
assigning the overall score to the data entity cluster.
19. The computer system of claim 15 , wherein the one or more hardware computer processors are further configured to execute the one or more software programs in order to cause the computer system to:
present, on an electronic display viewable by a user, a listing and/or summary of one or more of the plurality of data entity clusters according to the ranking.
20. The computer system of claim 19 , wherein the listing and/or summary presents the seed data entity associated with each of the one or more or the plurality of clusters.
21. The computer system of claim 15 , wherein the one or more hardware computer processors are further configured to execute the one or more software programs in order to cause the computer system to:
identify a second scoring strategy for prioritizing the plurality of data entity clusters;
for each data entity cluster:
evaluate one or more attributes of the collection of related data entities stored by the data entity cluster according to the second scoring strategy; and
assign a second score to the data entity cluster;
re-rank the plurality of data entity clusters according to the respective assigned second scores; and
present, on an electronic display viewable by a user, a listing and/or summary of one or more of the plurality of data entity clusters according to the re-ranking.