# US 2021/0279753 A1 · System and method for retail price optimization

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

- Number: US 2021/0279753 A1
- Document ID: US20210279753A1
- Status: Published application
- Kind: A1
- Application number: 16/807,214
- Filed: 2020-03-03
- Published: 2021-09-09
- Earliest claimed: 2020-03-03
- Assignees: Daisy Intelligence Corporation
- Applicants: Daisy Intelligence Corporation
- Inventors: Kari Saarenvirta
- Web page: https://patentgrep.com/patent/US20210279753A1

## CPC

- G06Q 30/0206: {Price or cost determination based on market factors}
- G06Q 10/067: Enterprise or organisation modelling
- G06Q 10/0674: {using process simulation}
- G06Q 30/0207: Discounts or incentives, e.g. coupons or rebates
- 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

## Abstract

A computer system and computer-implemented method for retail merchandise planning, including promotional product selection, price optimization and planning. According to one or more embodiments, the computer system for generating an electronic retail plan for a retailer comprises, a data staging module configured to input retail sensory data from one or more computer systems associated with the retailer; a data processing module configured to pre-process the inputted retail sensory data; a data warehouse module configured to store the inputted retail sensory data and the pre-processed retail sensory data; a state model module configured to generate a retailer state model for modeling operation of the retailer based on the retail sensory data; a calibration module configured to calibrate the state model module according to one or more control parameters; and an output module for generating an electronic retail plan for the retailer based on the retailer state model.

## Claims

### Claim 1

A method of generating an electronic retail price model and a selected control policy, the electronic retail price model and the selected control policy for generating an electronic retail price plan for retail operations performed within an enterprise network comprising a plurality of distributed computing devices, the plurality of distributed computing devices comprising a plurality of point-of-sale devices and a plurality of enterprise servers, the plurality of distributed computing devices in network communication, comprising:
receiving, at a first server of the plurality of enterprise servers, transaction data from the plurality of point-of-sale devices, the transaction data defined as a time series including a plurality of transaction data items corresponding to one or more previous time periods, the plurality of transaction data items comprising at least one of price data, product data, and customer data;
determining, at the first server, transformed transaction data based on the transaction data,
determining one or more features from the transformed transaction data;
determining one or more actionable features from the one or more features;
generating an electronic retail price model from the one or more actionable features; and
selecting a selected control policy for the electronic retail price model,
wherein the electronic retail price model and the selected control policy cooperate with an intelligent agent to determine the electronic retail price plan by simulating a plurality of simulated pricing decisions.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
transmitting the electronic retail price model to a second server in the plurality of enterprise servers.

### Claim 3 (depends on 2)

The method of claim 2, wherein the determining the one or more features from the transformed transaction data further comprises:
determining at least one of a plurality of cannibalization matrices, a plurality of cadence matrices, or a plurality of affinity matrices.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
the determining, at the first server, transformed transaction data based on the transaction data further comprises:
sorting the transaction data into a first transaction set and a second transaction set;
wherein the transformed transaction data further comprises a first transaction set comprising transactions having one or more promotional products, and a second transaction set comprising transactions having one or more non-promotional products.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
sorting the first transaction set into a promoted products set, a promoted item associated product set, and an associated product set;
wherein the first transaction set comprises the promoted products set, the promoted item associated product set, and the associated product set.

### Claim 6 (depends on 5)

The method of claim 5, wherein the determining the transformed transaction data further comprises:
determining one or more transaction values of the transaction data for each of the two or more previous time periods.

### Claim 7 (depends on 6)

The method of claim 6, wherein the selecting the selected control policy further comprises:
executing a reward function based on the retail data for each time period in the one or more time periods; and
selecting one or more coefficients that maximize the output of the reward function for the one or more time periods.

### Claim 8

A system for generating a retail price model and a selected control policy, the electronic retail price model and the selected control policy for generating an electronic retail price plan for retail operations performed within an enterprise network comprising a plurality of distributed computing devices, the plurality of distributed computing devices comprising a plurality of point-of-sale devices and a plurality of enterprise servers, the plurality of distributed computing devices in network communication, comprising:
a memory, the memory comprising:
transaction data from the plurality of point-of-sale devices, the transaction data defined as a time series including a plurality of transaction data items corresponding to one or more previous time periods, the plurality of transaction data items comprising at least one of price data, product data, and customer data
a processor in communication with the memory, the processor configured to:
determine transformed transaction data by,
determining one or more transaction values of the transaction data for each of the two or more previous time periods,
determine one or more features from the transformed transaction data;
determine one or more actionable features from the one or more features;
generate an electronic retail price model from the one or more actionable features;
store the electronic retail price model in the memory;
select a selected control policy for the retail promotional model, by,
executing a reward function based on the retail data for each time period in the one or more time periods; and
selecting one or more coefficients that maximize the output of the reward function for the one or more time periods, and
store the selected control policy in the memory;
wherein the electronic retail price model and the selected control policy cooperate to determine the electronic retail price plan by simulating a plurality of simulated pricing decisions.

### Claim 9 (depends on 8)

The system of claim 8, wherein the processor is further configured to:
transmit, using a network interface in communication with the processor, the electronic retail price model to a second server in the plurality of enterprise servers.

### Claim 10 (depends on 9)

The system of claim 9, wherein the processor is further configured to:
determine at least one of a plurality of cannibalization matrices, a plurality of cadence matrices, or a plurality of affinity matrices; and
store the at least one of a plurality of cannibalization matrices, a plurality of cadence matrices, or a plurality of affinity matrices in the memory.

### Claim 11 (depends on 10)

The system of claim 10, wherein the processor is further configured to:
determine, at the first server, transformed transaction data based on the transaction data further comprises:
sorting the transaction data into a first transaction set and a second transaction set;
wherein the transformed transaction data further comprises a first transaction set comprising transactions having one or more promotional products, and a second transaction set comprising transactions having one or more non-promotional products.

### Claim 12 (depends on 11)

The system of claim 11, wherein the processor is further configured to:
sort the first transaction set into a promoted products set, a promoted item associated product set, and an associated product set;
wherein the first transaction set comprises the promoted products set, the promoted item associated product set, and the associated product set.

### Claim 13 (depends on 12)

The system of claim 12, wherein the processor is further configured to determine the transformed transaction data further by:
determining one or more transaction values of the transaction data for each of the two or more previous time periods.

### Claim 14 (depends on 13)

The system of claim 13, wherein the processor is further configured to select the selected control policy further by:
executing a reward function based on the retail data for each time period in the one or more time periods; and
selecting one or more coefficients that maximize the output of the reward function for the one or more time periods.

### Claim 15

A method of generating an electronic retail price plan for retail operations performed within an enterprise network comprising a plurality of distributed computing devices, the plurality of distributed computing devices comprising a plurality of point-of-sale devices and a plurality of enterprise servers, the plurality of distributed computing devices in network communication, comprising:
receiving an electronic retail price model and a selected control policy;
simulating, using an intelligent agent, a plurality of simulated pricing decisions at a first hierarchy level for two or more future time periods using the electronic retail price model and the selected control policy, by,
determining, at the intelligent agent, for each product in the first hierarchy level, a plurality of simulated quantity forecasts corresponding to a plurality of simulated price levels;
determining, at the intelligent agent, an aggregated quantity and an aggregated price corresponding to the first hierarchy level based on the electronic retail price model and the selected control policy;
determining, at the intelligent agent, an item quantity and an item price for an item in the first hierarchy level based on the electronic retail price model and the selected control policy; and
determining, at the intelligent agent, a simulated reward value based on the item quantity, item price, aggregated quantity and aggregated price, and
generating an electronic retail price plan comprising a plurality of selected pricing decisions for two or more future time periods selected from the plurality of simulated pricing decisions, the plurality of selected pricing decisions comprising a plurality of price levels for a first product category, and a plurality of price levels for a second product category; and
wherein the first product category comprises pricing decisions for one or more promotional products, and the second product category comprises pricing decisions for one or more non-promotional products.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
transmitting the electronic retail price plan to a retail pricing system within the enterprise network.

### Claim 17 (depends on 16)

The method of claim 16, wherein the electronic retail price model further comprises at least one of a plurality of cannibalization matrices, a plurality of cadence matrices, or a plurality of affinity matrices.

### Claim 18 (depends on 17)

The method of claim 17, wherein the determining, at the intelligent agent, an aggregated quantity and an aggregated price corresponding to the first hierarchy level based on the electronic retail price model and the selected control policy further comprises:
determining a first hierarchy level affinity matrix based on the plurality of affinity matrices;
determining a first hierarchy level cadence matrix based on the plurality of affinity matrices;
determining a first hierarchy level cannibalization matrix based on the plurality of cannibalization matrices
determining the aggregated quantity based on the first hierarchy level affinity matrix, the first hierarchy level cadence matrix, and the first hierarchy level cannibalization matrix; and
determining the aggregated price based on the first hierarchy level affinity matrix, the first hierarchy level cadence matrix, and the first hierarchy level cannibalization matrix.

### Claim 19 (depends on 18)

The method of claim 18, wherein the determining, at the intelligent agent, an item quantity and an item price for an item in the first hierarchy level based on the electronic retail price model and the selected control policy further comprises:
determining a product affinity matrix based on the plurality of affinity matrices;
determining a product cadence matrix based on the plurality of affinity matrices;
determining a product cannibalization matrix based on the plurality of cannibalization matrices
determining the item quantity based on the product affinity matrix, the product cadence matrix, and the product cannibalization matrix; and
determining the item price based on the product affinity matrix, the product cadence matrix, and the product cannibalization matrix.

### Claim 20 (depends on 19)

The method of claim 19, further comprising:
receiving one or more configuration inputs, the one or more configuration inputs comprising a price minimum and a price maximum; and
wherein the determining the item price further comprises:
comparing the item price to the price minimum;
if the item price is below the price minimum, changing the item price to the price minimum;
comparing the item price to the price maximum;
if the item price is above the price maximum, changing the item price to the price maximum.

### Claim 21

A system for generating a retail price plan for retail operations performed within an enterprise network comprising a plurality of distributed computing devices, the plurality of distributed computing devices comprising a plurality of point-of-sale devices and a plurality of enterprise servers, the plurality of distributed computing devices in network communication, comprising:
a memory, the memory comprising:
an intelligent agent comprising:
an electronic retail price model; and
a selected control policy,
a processor in communication with the memory, the processor configured to:
operate the intelligent agent to simulate a plurality of simulated pricing decisions at a first hierarchy level for two or more future time periods using the electronic retail price model and the selected control policy, by,
determining, for each product in the first hierarchy level, a plurality of simulated quantity forecasts corresponding to a plurality of simulated price levels;
determining an aggregated quantity and an aggregated price corresponding to the first hierarchy level based on the electronic retail price model and the selected control policy;
determining an item quantity and an item price for an item in the first hierarchy level based on the electronic retail price model and the selected control policy;
determining a simulated reward value based on the item quantity, item price, aggregated quantity and aggregated price, and
generating an electronic retail price plan comprising a plurality of selected pricing decisions for two or more future time periods selected from the plurality of simulated pricing decisions.

### Claim 22 (depends on 21)

The system of claim 21, wherein the processor is further configured to:
transmit, using a network interface in communication with the processor, the electronic retail price plan to a retail pricing system within the enterprise network.

### Claim 23 (depends on 22)

The system of claim 22, wherein the electronic retail price model further comprises at least one of a plurality of cannibalization matrices, a plurality of cadence matrices, or a plurality of affinity matrices.

### Claim 24 (depends on 23)

The system of claim 23, wherein the processor is further configured to:
operate the intelligent agent to simulate a plurality of simulated pricing decisions at a first hierarchy level for two or more future time periods using the electronic retail price model and the selected control policy, by:
determining an aggregated quantity and an aggregated price corresponding to the first hierarchy level based on the electronic retail price model and the selected control policy, by:
determining a first hierarchy level affinity matrix based on the plurality of affinity matrices;
determining a first hierarchy level cadence matrix based on the plurality of affinity matrices;
determining a first hierarchy level cannibalization matrix based on the plurality of cannibalization matrices
determining the aggregated quantity based on the first hierarchy level affinity matrix, the first hierarchy level cadence matrix, and the first hierarchy level cannibalization matrix; and
determining the aggregated price based on the first hierarchy level affinity matrix, the first hierarchy level cadence matrix, and the first hierarchy level cannibalization matrix.

### Claim 25 (depends on 24)

The system of claim 24, wherein the processor is further configured to:
operate the intelligent agent to simulate a plurality of simulated pricing decisions at a first hierarchy level for two or more future time periods using the electronic retail price model and the selected control policy, by:
determining an item quantity and an item price for an item in the first hierarchy level based on the electronic retail price model and the selected control policy, by:
determining a product affinity matrix based on the plurality of affinity matrices;
determining a product cadence matrix based on the plurality of affinity matrices;
determining a product cannibalization matrix based on the plurality of cannibalization matrices
determining the item quantity based on the product affinity matrix, the product cadence matrix, and the product cannibalization matrix; and
determining the item price based on the product affinity matrix, the product cadence matrix, and the product cannibalization matrix.

### Claim 26 (depends on 25)

The system of claim 25, wherein the processor is further configured to:
receive one or more configuration inputs, the one or more configuration inputs comprising a price minimum and a price maximum; and
wherein the determining the item price further comprises:
comparing the item price to the price minimum;
if the item price is below the price minimum, changing the item price to the price minimum;
comparing the item price to the price maximum;
if the item price is above the price maximum, changing the item price to the price maximum.
