US 11,734,711 B2
Systems and methods for intelligent promotion design with promotion scoring
Michael Montero, Palo Alto, CA (US)
Assigned to Eversight, Inc., San Francisco, CA (US)
Filed by Eversight, Inc., Palo Alto, CA (US)
Filed on Apr. 26, 2021, as Appl. No. 17/240,299.
Application 17/240,299 is a continuation of application No. 15/597,132, filed on May 16, 2017, granted, now 10,991,001.
Prior Publication US 2021/0319472 A1, Oct. 14, 2021
Int. Cl. G06Q 30/02 (2023.01); G06Q 30/0242 (2023.01); G06Q 30/0251 (2023.01); G06Q 30/0201 (2023.01); G06Q 30/0207 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 30/0244 (2013.01) [G06Q 30/0201 (2013.01); G06Q 30/0239 (2013.01); G06Q 30/0271 (2013.01); G06N 20/00 (2019.01)] 16 Claims
OG exemplary drawing
 
1. A method for selecting a set of offers comprising:
defining, by one or more processors, values for a plurality of variables;
applying, by one or more processors, heuristics to filter a set of possible offers to a first set of offers;
generating, by one or more processors, an offer vector for each offer in the first set of offers, wherein each offer vector includes a variable value for each variable of the plurality of variables and a success metric of the offer corresponding to the offer vector, wherein the success metric of the offer is a weighted composite of at least two of redemption rates, speed of deletion, shares, and saves;
generating, by one or more processors, a derivative table based on the generated offer vectors, wherein the derivative table comprises a plurality of differential vectors, wherein each differential vector comprises pair-wise differences between variable values for a pair of the generated offer vectors and a differential success score representing a difference of the success metrics of the pair of generated offer vectors;
training, by one or more processors, at least one of a neural network or a decision tree based on the derivative table;
generating, by one or more processors, a score for each offer in the first set of offers using the at least one of a neural network or a decision tree;
generating, by one or more processors, correlations of the variable values to the generated scores to identify winning variable values;
generating, by one or more processors, a test set of offers using permutations of the winning variable values; and
transmitting the set of test offers to a plurality of users.