Measuring impact of events on affinity cluster using propensity dimensions
A system and method including building propensity inclination dimensions of an affinity cluster, the propensity inclination dimensions maintained at a group profile level of the affinity cluster, identifying next best priority signals based on influencing events to determine a next best priority, applying a predictive algorithm to derive an influencing index, which is used to determine a tolerance level of the affinity cluster, deriving a duration of time of the tolerance level, and determining a critical mass of the affinity cluster required to achieve an objective of an organization.
1 . A method comprising:
building, by a processor of a computing system, propensity inclination dimensions of an affinity cluster, the propensity inclination dimensions maintained at a group profile level of the affinity cluster;
identifying, by the processor, next best priority signals based on influencing events to determine a next best priority;
applying, by the processor, a predictive algorithm to derive an influencing index, which is used to determine a tolerance level of the affinity cluster;
deriving, by the processor, a duration of time of the tolerance level;
determining, by the processor and using a machine learning model, a critical mass of the affinity cluster required to achieve an objective of an organization, wherein the machine learning model is based on a cost function to optimize the critical mass based on the propensity inclination dimensions;
predicting, by the processor, a potential reciprocal impact to the organization based on a propensity inclination of the affinity cluster from non-controlled dimensions, wherein an impact from a deviation of the affinity cluster from a defined goal is predicted;
simulating, by the processor, the impact from the deviation across the affinity cluster to forecast a recovery time to the defined goal; and
automatically triggering, by the processor, implementation of an incentive mechanism to mitigate the deviation of the affinity cluster or protect assets of the organization.
2 . The method of claim 1 , further comprising
determining, by the processor, an influencing activity period for the affinity cluster by predicting a threshold value of change of the influencing index, as a result of ripple effect from plurality of influencing events.
3 . The method of claim 2 , further comprising
applying, by the processor, a regression model for the influencing activity period, the next best priority, and the propensity inclination dimensions to determine controlled dimensions.
4 . The method of claim 1 , further comprising
determining, by the processor, a linkage strength using the influencing index of each propensity inclination dimension for the influencing events and a probability of a next influencing event within an optimum time window that can change the influencing index by a minimum threshold.
5 . The method of claim 1 ,
wherein the next best priority is any future event or activity that can occur that might have priority or importance to the affinity cluster.
6 . The method of claim 1 ,
wherein the influencing index is a distance between two consecutive next best priorities correlated under two or more consecutive influencing events and other correlated propensity values of the affinity cluster.
7 . The method of claim 1 , further comprising
determining, by the processor, an optimal cardinality of the next best priority to reconstruct the affinity cluster.
8 . A computing system, comprising:
one or more processors; and
one or more memory devices coupled to the one or more processors, wherein the one or more processors are configured to:
build propensity inclination dimensions of an affinity cluster, the propensity inclination dimensions maintained at a group profile level of the affinity cluster;
identify next best priority signals based on influencing events to determine a next best priority;
apply a predictive algorithm to derive an influencing index, which is used to determine a tolerance level of the affinity cluster;
derive a duration of time of the tolerance level;
determine, using a machine learning model, a critical mass of the affinity cluster required to achieve an objective of an organization, wherein the machine learning model is based on a cost function to optimize the critical mass based on the propensity inclination dimensions;
predict a potential reciprocal impact to the organization based on a propensity inclination of the affinity cluster from non-controlled dimensions, wherein an impact from a deviation of the affinity cluster from a defined goal is predicted;
simulate the impact from the deviation across the affinity cluster to forecast a recovery time to the defined goal; and
automatically trigger implementation of an incentive mechanism to mitigate the deviation of the affinity cluster or protect assets of the organization.
9 . The computing system of claim 8 ,
wherein the one or more processors are further configured to:
determine an influencing activity period for the affinity cluster by predicting a threshold value of change of the influencing index, as a result of ripple effect from plurality of influencing events.
10 . The computing system of claim 9 ,
wherein the one or more processors are further configured to:
apply a regression model for the influencing activity period, the next best priority, and the propensity inclination dimensions to determine controlled dimensions.
11 . The computing system of claim 8 ,
wherein the one or more processors are further configured to:
determine a linkage strength using the influencing index of each propensity inclination dimension for the influencing events and a probability of a next influencing event within an optimum time window that can change the influencing index by a minimum threshold.
12 . The computing system of claim 8 ,
wherein the next best priority is any future event or activity that can occur that might have priority or importance to the affinity cluster.
13 . The computing system of claim 8 ,
wherein the influencing index is a distance between two consecutive next best priorities correlated under two or more consecutive influencing events and other correlated propensity values of the affinity cluster.
14 . The computing system of claim 8 ,
wherein the one or more processors are further configured to:
determine an optimal cardinality of the next best priority to reconstruct the affinity cluster.
15 . A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
build propensity inclination dimensions of an affinity cluster, the propensity inclination dimensions maintained at a group profile level of the affinity cluster;
identify next best priority signals based on influencing events to determine a next best priority;
apply a predictive algorithm to derive an influencing index, which is used to determine a tolerance level of the affinity cluster;
derive, using a machine learning model, a duration of time of the tolerance level;
determine a critical mass of the affinity cluster required to achieve an objective of an organization, wherein the machine learning model is based on a cost function to optimize the critical mass based on the propensity inclination dimensions;
predict a potential reciprocal impact to the organization based on a propensity inclination of the affinity cluster from non-controlled dimensions, wherein an impact from a deviation of the affinity cluster from a defined goal is predicted;
simulate the impact from the deviation across the affinity cluster to forecast a recovery time to the defined goal; and
automatically trigger implementation of an incentive mechanism to mitigate the deviation of the affinity cluster or protect assets of the organization.
16 . The non-transitory computer-readable medium of claim 15 ,
wherein the one or more instructions cause the device to:
determine an influencing activity period for the affinity cluster by predicting a threshold value of change of the influencing index, as a result of ripple effect from plurality of influencing events.
17 . The non-transitory computer-readable medium of claim 16 ,
wherein the one or more instructions cause the device to:
apply a regression model for the influencing activity period, the next best priority, and the propensity inclination dimensions to determine controlled dimensions.
18 . The non-transitory computer-readable medium of claim 15 ,
wherein the one or more instructions cause the device to:
determine a linkage strength using the influencing index of each propensity inclination dimension for the influencing events and a probability of a next influencing event within an optimum time window that can change the influencing index by a minimum threshold.
19 . The non-transitory computer-readable medium of claim 15 ,
wherein the next best priority is any future event or activity that can occur that might have priority or importance to the affinity cluster.
20 . The non-transitory computer-readable medium of claim 15 ,
wherein the influencing index is a distance between two consecutive next best priorities correlated under two or more consecutive influencing events and other correlated propensity values of the affinity cluster.