# US 2023/0245164 A1 · Systems and methods for intelligent promotion design with promotion scoring

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0245164 A1
- Document ID: US20230245164A1
- Status: Published application
- Kind: A1
- Application number: 18/295,767
- Filed: 2023-04-04
- Published: 2023-08-03
- Earliest claimed: 2017-05-16
- Assignees: Eversight, Inc.
- Applicants: Eversight, Inc.
- Inventors: Michael Montero
- Web page: https://patentgrep.com/patent/US20230245164A1

## CPC

- G06Q 30/0244: {Optimization}
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 30/0239: {Online discounts or incentives}
- G06Q 30/0271: {Personalized advertisement}
- G06N 3/08: Learning methods
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods for scoring promotions are provided. A set of training offers are received, which include combinations of variable values. These combinations of variable values are converted into a vector value. The offers are paired and the vectors subtracted from one another, resulting in a pair vector. Metrics for the success of offers is collected, and are subtracted from one another for the paired offers to generate a raw score. This raw score is then normalized using the pair vector. The normalized scores are utilized to generate a model for the impact any variable value has on offer success, which may then be applied, using linear regression, to new offers to generate an expected level of success. The new scored offers are ranked and the top-ranked offers are selected for inclusion in a promotional campaign.

## Claims

### Claim 1

A method for selecting a set of offers comprising:
receiving, by one or more processors, a first set of candidate offers, wherein each candidate offer in the first set of candidate offers includes a variable value for each of a plurality of variables;
generating, by one or more processors, an offer vector for each offer in the first set of candidate offers, wherein each offer vector includes the variable values for the corresponding candidate offer of the first set of candidate offers, and wherein each offer vector includes a success metric for the candidate offer;
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, a machine-learning model based on the derivative table, wherein the machine-learning model is trained to predict a success metric for an offer based on an offer vector associated with the offer;
identifying, by one or more processors, a set of test offers by applying the machine-learning model to offer vectors corresponding to candidate offers in a second set of candidate offers; and
transmitting, by one or more processors, the set of test offers to a plurality of users.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
selecting an additional set of offers by computing an orthogonality of the offer vectors to the candidate offers in the second set of candidate offers to the set of test offers; and
transmitting the additional set of offers to the plurality of users.

### Claim 3 (depends on 2)

The method of claim 2, wherein computing an orthogonality of the offer vectors comprises:
generating a matrix of comprising variable values corresponding to the set of test offers and variable values corresponding to the additional set of offers; and
optimizing for a maximum determinant of the matrix by selecting the additional set of offers to maximize the determinant of the matrix.

### Claim 4 (depends on 1)

The method of claim 1, wherein identifying the set of test offers comprises:
ranking the second set of candidate offers based on a corresponding success metric; and
selecting the set of test offers based on the ranking.

### Claim 5 (depends on 1)

The method of claim 1, wherein transmitting the set of test offers to a plurality of users comprises transmitting the set of test offers to a set of segmented users.

### Claim 6 (depends on 1)

The method of claim 1, wherein the machine-learning model comprises a neural network or a decision tree.

### Claim 7 (depends on 1)

The method of claim 1, wherein receiving the first set of candidate offers comprises:
receiving an initial set of candidate offers; and
generating the first set of candidate offers by applying a set of heuristics to filter the initial set of candidate offers.

### Claim 8 (depends on 7)

The method of claim 7, wherein the initial set of candidate offers comprises a candidate offer for each possible combinations of variable values for the plurality of variables.

### Claim 9 (depends on 7)

The method of claim 7, wherein the set of heuristics comprises a user-defined heuristic.

### Claim 10 (depends on 1)

The method of claim 1, wherein the success metric for a candidate offer is based on a clip rate of the candidate offer.

### Claim 11

A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
receiving, by one or more processors, a first set of candidate offers, wherein each candidate offer in the first set of candidate offers includes a variable value for each of a plurality of variables;
generating, by one or more processors, an offer vector for each offer in the first set of candidate offers, wherein each offer vector includes the variable values for the corresponding candidate offer of the first set of candidate offers, and wherein each offer vector includes a success metric for the candidate offer;
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, a machine-learning model based on the derivative table, wherein the machine-learning model is trained to predict a success metric for an offer based on an offer vector associated with the offer;
identifying, by one or more processors, a set of test offers by applying the machine-learning model to offer vectors corresponding to candidate offers in a second set of candidate offers; and
transmitting, by one or more processors, the set of test offers to a plurality of users.

### Claim 12 (depends on 11)

The computer-readable medium of claim 11, further storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
selecting an additional set of offers by computing an orthogonality of the offer vectors to the candidate offers in the second set of candidate offers to the set of test offers; and
transmitting the additional set of offers to the plurality of users.

### Claim 13 (depends on 12)

The computer-readable medium of claim 12, wherein computing an orthogonality of the offer vectors comprises:
generating a matrix of comprising variable values corresponding to the set of test offers and variable values corresponding to the additional set of offers; and
optimizing for a maximum determinant of the matrix by selecting the additional set of offers to maximize the determinant of the matrix.

### Claim 14 (depends on 11)

The computer-readable medium of claim 11, wherein identifying the set of test offers comprises:
ranking the second set of candidate offers based on a corresponding success metric; and
selecting the set of test offers based on the ranking.

### Claim 15 (depends on 11)

The computer-readable medium of claim 11, wherein transmitting the set of test offers to a plurality of users comprises transmitting the set of test offers to a set of segmented users.

### Claim 16 (depends on 11)

The computer-readable medium of claim 11, wherein the machine-learning model comprises a neural network or a decision tree.

### Claim 17 (depends on 11)

The computer-readable medium of claim 11, wherein receiving the first set of candidate offers comprises:
receiving an initial set of candidate offers; and
generating the first set of candidate offers by applying a set of heuristics to filter the initial set of candidate offers.

### Claim 18 (depends on 17)

The computer-readable medium of claim 17, wherein the initial set of candidate offers comprises a candidate offer for each possible combinations of variable values for the plurality of variables.

### Claim 19 (depends on 17)

The computer-readable medium of claim 17, wherein the set of heuristics comprises a user-defined heuristic.

### Claim 20 (depends on 11)

The computer-readable medium of claim 11, wherein the success metric for a candidate offer is based on a clip rate of the candidate offer.
