Systems and methods for detecting and scoring anomalies
First Claim
1. A computer-implemented method for analyzing a plurality of first digital interactions observed from a first time period, the method comprising acts of:
- (A) identifying a plurality of first values of an attribute, each value of the plurality of first values corresponding respectively to a digital interaction of the plurality of first digital interactions observed from the first time period;
(B) dividing the plurality of first values into a plurality of buckets;
(C) for at least one bucket of the plurality of buckets, determining a count of values from the plurality of first values that fall within the at least one bucket;
(D) comparing, by at least one processor, the count of values from the plurality of first values that fall within the at least one bucket against historical information regarding the attribute, wherein;
the historical information regarding the attribute comprises an expected count for the at least one bucket;
the count of values from the plurality of first values that fall within the at least one bucket is compared against the expected count for the at least one bucket;
the expected count for the at least one bucket comprises a count of values from a plurality of second values of the attribute that fall within the at least one bucket;
each value of the plurality of second values corresponds respectively to a digital interaction of a plurality of second digital interactions;
the plurality of second digital interactions were observed from a second time period, the second time period having a same length as the first time period; and
the first time period occurs after the second time period;
(E) determining whether the attribute is anomalous over the first time period, based at least in part on a result of the act (D); and
(F) in response to determining that the attribute is anomalous over the first time period, storing, in a profile, information regarding the attribute.
2 Assignments
0 Petitions
Accused Products
Abstract
Systems and methods for detecting and scoring anomalies. In some embodiments, a method is provided, comprising acts of: (A) identifying a plurality of values of an attribute, each value of the plurality of values corresponding respectively to a digital interaction of the plurality of digital interactions; (B) dividing the plurality of values into a plurality of buckets; (C) for at least one bucket of the plurality of buckets, determining a count of values from the plurality of values that fall within the at least one bucket; (D) comparing the count of values from the plurality of values that fall within the at least one bucket against historical information regarding the attribute; and (E) determining whether the attribute is anomalous based at least in part on a result of the act (D).
-
Citations
28 Claims
-
1. A computer-implemented method for analyzing a plurality of first digital interactions observed from a first time period, the method comprising acts of:
-
(A) identifying a plurality of first values of an attribute, each value of the plurality of first values corresponding respectively to a digital interaction of the plurality of first digital interactions observed from the first time period; (B) dividing the plurality of first values into a plurality of buckets; (C) for at least one bucket of the plurality of buckets, determining a count of values from the plurality of first values that fall within the at least one bucket; (D) comparing, by at least one processor, the count of values from the plurality of first values that fall within the at least one bucket against historical information regarding the attribute, wherein; the historical information regarding the attribute comprises an expected count for the at least one bucket; the count of values from the plurality of first values that fall within the at least one bucket is compared against the expected count for the at least one bucket; the expected count for the at least one bucket comprises a count of values from a plurality of second values of the attribute that fall within the at least one bucket; each value of the plurality of second values corresponds respectively to a digital interaction of a plurality of second digital interactions; the plurality of second digital interactions were observed from a second time period, the second time period having a same length as the first time period; and the first time period occurs after the second time period; (E) determining whether the attribute is anomalous over the first time period, based at least in part on a result of the act (D); and (F) in response to determining that the attribute is anomalous over the first time period, storing, in a profile, information regarding the attribute. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system for analyzing a plurality of first digital interactions observed from a first time period, the system comprising:
-
at least one processor; and at least one computer-readable storage device having stored thereon executable instructions which, when executed, program the at least one processor to perform a method comprising acts of; (A) identifying a plurality of first values of an attribute, each value of the plurality of first values corresponding respectively to a digital interaction of the plurality of first digital interactions observed from the first time period; (B) dividing the plurality of first values into a plurality of buckets; (C) for at least one bucket of the plurality of buckets, determining a count of values from the plurality of first values that fall within the at least one bucket; (D) comparing the count of values from the plurality of first values that fall within the at least one bucket against historical information regarding the attribute, wherein; the historical information regarding the attribute comprises an expected count for the at least one bucket; the count of values from the plurality of first values that fall within the at least one bucket is compared against the expected count for the at least one bucket; the expected count for the at least one bucket comprises a count of values from a plurality of second values of the attribute that fall within the at least one bucket; each value of the plurality of second values corresponds respectively to a digital interaction of a plurality of second digital interactions; the plurality of second digital interactions were observed from a second time period, the second time period having a same length as the first time period; and the first time period occurs after the second time period; (E) determining whether the attribute is anomalous over the first time period, based at least in part on a result of the act (D); and (F) in response to determining that the attribute is anomalous over the first time period, storing, in a profile, information regarding the attribute. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. A computer-implemented method for analyzing a plurality of digital interactions over a time period, the method comprising acts of:
-
(A) identifying a plurality of values of an attribute, each value of the plurality of values corresponding respectively to a digital interaction of the plurality of digital interactions; (B) dividing the plurality of values into a plurality of first buckets; (C) for at least one bucket of the plurality of first buckets, determining a count of values from the plurality of values that fall within the at least one bucket; (D) comparing, by at least one processor, the count of values from the plurality of values that fall within the at least one bucket against historical information regarding the attribute, wherein; the historical information regarding the attribute comprises an expected count for the at least one bucket; and the count of values from the plurality of first values that fall within the at least one bucket is compared against the expected count for the at least one bucket; (E) determining whether the attribute is anomalous over the time period, based at least in part on a result of the act (D), comprising; determining if the count of values from the plurality of values that fall within the at least one bucket exceeds the expected count for the at least one bucket by at least a selected threshold amount; and in response to determining that the count of values that fall within the at least one bucket exceeds the expected count for the at least one bucket by at least the selected threshold amount, dividing the plurality of values into a plurality of second buckets, wherein there are more second buckets than first buckets; and (F) in response to determining that the attribute is anomalous over the time period, storing, in a profile, information regarding the attribute. - View Dependent Claims (18, 19, 20, 21, 22)
-
-
23. A system for analyzing a plurality of digital interactions over a time period, the system comprising:
-
at least one processor; and at least one computer-readable storage device having stored thereon executable instructions which, when executed, program the at least one processor to perform a method comprising acts of; (A) identifying a plurality of values of an attribute, each value of the plurality of values corresponding respectively to a digital interaction of the plurality of digital interactions; (B) dividing the plurality of values into a plurality of first buckets; (C) for at least one bucket of the plurality of first buckets, determining a count of values from the plurality of values that fall within the at least one bucket; (D) comparing the count of values from the plurality of values that fall within the at least one bucket against historical information regarding the attribute, wherein; the historical information regarding the attribute comprises an expected count for the at least one bucket; and the count of values from the plurality of first values that fall within the at least one bucket is compared against the expected count for the at least one bucket; (E) determining whether the attribute is anomalous over the time period, based at least in part on a result of the act (D), comprising; determining if the count of values from the plurality of values that fall within the at least one bucket exceeds the expected count for the at least one bucket by at least a selected threshold amount; and in response to determining that the count of values that fall within the at least one bucket exceeds the expected count for the at least one bucket by at least the selected threshold amount, dividing the plurality of values into a plurality of second buckets, wherein there are more second buckets than first buckets; and (F) in response to determining that the attribute is anomalous over the time period, storing, in a profile, information regarding the attribute. - View Dependent Claims (24, 25, 26, 27, 28)
-
Specification