System, method, and computer program for identifying significant records
A system, method, and computer program product are provided for identifying significant records (e.g. journeys, etc.). In use, a plurality of records including a plurality of events are stored. Further, an indication is received regarding at least one subset of the records. Thereafter, at least a portion of the events of the at least one subset of the records are processed to generate mean information such that the records of the at least one subset may be compared, utilizing the mean information. This may be accomplished while avoiding, at least in part, a covariance calculation, or in such a manner that the comparison is independent of such covariance calculation. A result of the comparison may be displayed.
1. A computer program product embodied on a non-transitory computer readable medium, comprising computer code for:
storing, in a database, a plurality of records for a plurality of customers, each record of the plurality of records storing an event sequence associated with customer interactions that includes a plurality of events of different event types;
receiving, via an input device, an indication of one or more aspects associated with one or more of the records;
identifying, based on the indication, a subset of the records having the one or more aspects, the subset including at least two of the records;
processing, utilizing at least one processor, events included in the subset of the records by:
identifying, for each record in the subset of records, an anchor event included therein, the anchor event being an event for which a decision of significance is to be tested,
identifying, for each record in the subset of records, a first subset of events included therein occurring before the anchor event identified for the record and a second subset of events included therein occurring after the anchor event identified for the record,
determining a target measurement value from one of the records in the subset of the records,
calculating a mean measurement value the records in the subset of the records according to the target measurement value, the mean measurement value calculated using the equation:
μ
^
=
1
n
∑
i
=
1
n
X
io
wherein i is the record identifier of the record,
wherein X io is a measurement value for the record,
calculating a variance measurement value based on the mean measurement value, the variance measurement value calculated using the equation:
σ
^
2
=
n
[
μ
^
(
1
-
μ
^
)
2
+
μ
^
2
(
1
-
μ
^
)
]
n
-
1
;
comparing, utilizing the at least one processor, the records in the subset of the records, utilizing the mean measurement value and the variance measurement value, to identify a particular event in a particular record of the subset of the records that causes the particular record to deviate from other records in the subset of the records; and
displaying, via at least one display, an indication of the particular event of the particular record of the subset of the records that causes the particular record to deviate from other records in the subset of the records.
2. The computer program product of claim 1 , wherein the target measurement value is a value of a binary condition, and wherein the measurement value for the record is a value of the binary condition assigned to the record.
3. The computer program product of claim 2 , wherein the binary condition includes success and fail values.
4. The computer program product of claim 2 , wherein the binary condition includes a first value indicating that a particular event is present and a second value indicating that the particular event is not present.
5. The computer program product of claim 1 , further comprising computer code for:
changing at least one business rule, based on the indication of the particular event of the particular record of the subset of the records that causes the particular record to deviate from other records in the subset of the records.
6. The computer program product of claim 1 , wherein the comparison including calculating a modified t-statistic using the equation:
t
AB
=
σ
A
2
+
σ
B
2
n
B
.
7. A method, comprising:
storing, in a database, a plurality of records for a plurality of customers, each record of the plurality of records storing an event sequence associated with customer interactions that includes a plurality of events of different event types;
receiving, via an input device, an indication of one or more aspects associated with one or more of the records;
identifying, based on the indication, a subset of the records having the one or more aspects, the subset including at least two of the records;
processing, utilizing at least one processor, events included in the subset of the records by:
identifying, for each record in the subset of records, an anchor event included therein, the anchor event being an event for which a decision of significance is to be tested,
identifying, for each record in the subset of records, a first subset of events included therein occurring before the anchor event identified for the record and a second subset of events included therein occurring after the anchor event identified for the record,
determining a target measurement value from one of the records in the subset of the records,
calculating a mean measurement value the records in the subset of the records according to the target measurement value, the mean measurement value calculated using the equation:
μ
^
=
1
n
∑
i
=
1
n
X
io
wherein i is the record identifier of the record,
wherein X io is a measurement value for the record,
calculating a variance measurement value based on the mean measurement value, the variance measurement value calculated using the equation;
σ
^
2
=
n
[
μ
^
(
1
-
μ
^
)
2
+
μ
^
2
(
1
-
μ
^
)
]
n
-
1
;
comparing, utilizing the at least one processor, the records in the subset of the records, utilizing the mean measurement value and the variance measurement value, to identify a particular event in a particular record of the subset of the records that causes the particular record to deviate from other records in the subset of the records; and
displaying, via at least one display, an indication of the particular event of the particular record of the subset of the records that causes the particular record to deviate from other records in the subset of the records.
8. A system, comprising:
one or more hardware processors for:
storing, in a database, a plurality of records for a plurality of customers, each record of the plurality of records storing an event sequence associated with customer interactions that includes a plurality of events of different event types;
receiving, via an input device, an indication of one or more aspects associated with one or more of the records;
identifying, based on the indication, a subset of the records having the one or more aspects, the subset including at least two of the records;
processing vents included in the subset of the records by:
identifying, for each record in the subset of records, an anchor event included therein, the anchor event being an event for which a decision of significance is to be tested,
identifying, for each record in the subset of records, a first subset of events included therein occurring before the anchor event identified for the record and a second subset of events included therein occurring after the anchor event identified for the record,
determining a target measurement value from one of the records in the subset of the records,
calculating a mean measurement value the records in the subset of the records according to the target measurement value, the mean measurement value calculated using the equation:
μ
^
=
1
n
∑
i
=
1
n
X
io
wherein i is the record identifier of the record,
wherein X io is a measurement value for the record,
calculating a variance measurement value based on the mean measurement value, the variance measurement value calculated using the equation:
σ
^
2
=
n
[
μ
^
(
1
-
μ
^
)
2
+
μ
^
2
(
1
-
μ
^
)
]
n
-
1
;
comparing the records in the subset of the records, utilizing the mean measurement value and the variance measurement value, to identify a particular event in a particular record of the subset of the records that causes the particular record to deviate from other records in the subset of the records; and
displaying, via at least one display, an indication of the particular event of the particular record of the subset of the records that causes the particular record to deviate from other records in the subset of the records.