US 12,086,822 B2
Crisis-recovery data analytics engine in a data analytics system
Vincent Francois Faber, Boston, MA (US); Daniele Gaudenzio Wolfgang Parenti, Marina Del Rey, CA (US); and Aaron Dean Arnoldsen, Beaverton, OR (US)
Assigned to THE BOSTON CONSULTING GROUP, INC., Boston, MA (US)
Filed by The Boston Consulting Group, Inc., Boston, MA (US)
Filed on May 18, 2022, as Appl. No. 17/747,927.
Claims priority of provisional application 63/234,232, filed on Aug. 17, 2021.
Prior Publication US 2023/0091245 A1, Mar. 23, 2023
Int. Cl. G06Q 30/0204 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 30/0205 (2013.01) [G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computerized system comprising:
one or more computer processors; and
computer memory storing computer-useable instructions that, when used by the one or more computer processors, cause the one or more computer processors to perform operations comprising:
generating, by the computerized system, a training data set, wherein generating the training data set comprises aggregating, by the computerized system at a crisis-recovery data analytics engine, a pre-crisis dataset and a crisis dataset associated with a set of variables representing a set of consumer behaviors;
training, by the computerized system, a crisis-recovery machine learning model based on the training data set, wherein training the crisis-recovery machine learning model comprises:
determining weights for the set of variables,
determining a linear combination of the set of variables based on the weights, wherein the linear combination represents a calculation of a consumer activity index corresponding to the set of variables, and wherein the consumer activity index represents a level of recovery from a crisis event;
reducing a dimensionality of the linear combination, wherein reducing the dimensionality of the linear combination comprises selecting a subset of the set of variables using principal component analysis to calculate the consumer activity index;
accessing, by the computerized system, a crisis-recovery dataset associated with the subset of variables;
generating, by the computerized system using the linear combination, the consumer activity index for each of several periods in time; and
based on the consumer activity index, generating, by the computer system, an interactive user interface for presentation to a user, wherein the interactive user interface comprises a data visualization of the subset of variables and a plot of the consumer activity index for each of the several periods in time.