# US 12,182,728 B1 · Price-demand elasticity as feature in machine learning model for demand forecasting

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

- Number: US 12,182,728 B1
- Document ID: US12182728B1
- Status: Granted
- Kind: B1
- Application number: 17/166,563
- Filed: 2021-02-03
- Granted: 2024-12-31
- Earliest claimed: 2020-03-02
- Assignees: Blue Yonder Group, Inc.
- Applicants: Blue Yonder Group, Inc.
- Inventors: Felix Christopher Wick; Shyam Narasimhan
- Web page: https://patentgrep.com/patent/US12182728B1

## CPC

- G06N 5/04: Inference or reasoning models
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q 30/0206: {Price or cost determination based on market factors}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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 system and method are disclosed to identify one or more price-demand elasticity causal factors and to forecast demand using the one or more price-demand elasticity causal factors. Embodiments include a computer comprising a processor and memory. Embodiments train a machine learning model to identify one or more external causal factors that influence demand for one or more products. Embodiments train the machine learning model to generate one or more price-demand elasticity causal factors to predict a target outcome for a given product demand. Embodiments predict, with the machine learning model, a demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors.

## Claims

### Claim 1

A computer-implemented method, comprising:
training, by a first iterative approach comprising cyclic boosting in multiplicative mode, a machine learning model to identify one or more external causal factors that influence demand for one or more products;
training, by a second iterative approach comprising cyclic boosting in multiplicative mode that cycles through features and parameters, the machine learning model to generate one or more price-demand elasticity causal factors to predict a target outcome for a given product demand;
predicting, with the machine learning model, a demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors, wherein the machine learning model is a first machine learning model, the one or more price-demand elasticity causal factors is one or more first price-demand elasticity causal factors the target outcome is a first target outcome and the demand is a first demand;
deconfounding historical demand data for the one or more products;
training a second machine learning model to generate, based on the deconfounded historical demand data for the one or more products, one or more second price-demand elasticity causal factors to predict a second target outcome for the given product demand;
predicting, with the second machine learning model, a second demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more second price-demand elasticity causal factors; and
shaping the predicted second demand for the one or more products by altering one or more product price variables of the one or more products.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
transmitting, by the computer and in response to the predicted demand for the one or more products, instructions to alter actions at one or more supply chain entities, the instructions comprising one or more of:
an instruction to increase capacity at one or more supply chain entity locations;
an instruction to alter product supply levels at the one or more supply chain entities;
an instruction to adjust product mix ratios at the one or more supply chain entities; and
an instruction to alter the configuration of packaging of one or more products sold by the one or more supply chain entities.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, further comprising:
displaying, on an output device, the predicted demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
predicting, with the second machine learning model, a third demand for the one or more products based, at least in part, on the identified one or more external causal factors, the generated one or more second price-demand elasticity causal factors, and the shaped predicted second demand for the one or more products.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
deconfounding the historical demand data for the one or more products by conducting one or more randomized controlled A/B group trials to deconfound one or more cause-effect relationships of the historical demand data and corresponding causal variable data from one or more potential confounding variables.

### Claim 6

A system, comprising:
a computer, comprising a processor and memory, the computer configured to:
train, by a first iterative approach comprising cyclic boosting in multiplicative mode, a machine learning model to identify one or more external causal factors that influence demand for one or more products;
train, by a second iterative approach comprising cyclic boosting in multiplicative mode that cycles through features and parameters, the machine learning model to generate one or more price-demand elasticity causal factors to predict a target outcome for a given product demand;
predict, with the machine learning model, a demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors, wherein the machine learning model is a first machine learning model, the one or more price-demand elasticity causal factors is one or more first price-demand elasticity causal factors the target outcome is a first target outcome, the demand is a first demand and the computer is further configured to:
deconfound historical demand data for the one or more products;
train a second machine learning model to generate, based on the deconfounded historical demand data for the one or more products, one or more second price-demand elasticity causal factors to predict a second target outcome for the given product demand;
predict, with the second machine learning model, a second demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more second price-demand elasticity causal factors; and
shape the predicted second demand for the one or more products by altering one or more product price variables of the one or more products.

### Claim 7 (depends on 6)

The system of claim 6, wherein the computer is further configured to transmit, in response to the predicted demand for the one or more products, instructions to alter actions at one or more supply chain entities, the instructions comprising one or more of:
an instruction to increase capacity at one or more supply chain entity locations;
an instruction to alter product supply levels at the one or more supply chain entities;
an instruction to adjust product mix ratios at the one or more supply chain entities; and
an instruction to alter the configuration of packaging of one or more products sold by the one or more supply chain entities.

### Claim 8 (depends on 6)

The system of claim 6, wherein the compute is further configured to:
display, on an output device, the predicted demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors.

### Claim 9 (depends on 6)

The system of claim 6, further comprising the computer:
predicting, with the second machine learning model, a third demand for the one or more products based, at least in part, on the identified one or more external causal factors, the generated one or more second price-demand elasticity causal factors, and the shaped predicted second demand for the one or more products.

### Claim 10 (depends on 6)

The system of claim 6, wherein the computer is further configured to:
deconfound the historical demand data for the one or more products by conducting one or more randomized controlled A/B group trials to deconfound one or more cause-effect relationships of the historical demand data and corresponding causal variable data from one or more potential confounding variables.

### Claim 11

A non-transitory computer-readable storage medium embodied with software, the software when executed configured to:
train, by a first iterative approach comprising cyclic boosting in multiplicative mode, a machine learning model to identify one or more external causal factors that influence demand for one or more products;
train, by a second iterative approach comprising cyclic boosting in multiplicative mode that cycles through features and parameters, the machine learning model to generate one or more price-demand elasticity causal factors to predict a target outcome for a given product demand;
predict, with the machine learning model, a demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors, wherein the machine learning model is a first machine learning model, the one or more price-demand elasticity causal factors is one or more first price-demand elasticity causal factors the target outcome is a first target outcome, the demand is a first demand and the software when executed is further configured to:
deconfound historical demand data for the one or more products;
train a second machine learning model to generate, based on the deconfounded historical demand data for the one or more products, one or more second price-demand elasticity causal factors to predict a second target outcome for the given product demand;
predict, with the second machine learning model, a second demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more second price-demand elasticity causal factors; and
shape the predicted second demand for the one or more products by altering one or more product price variables of the one or more products.

### Claim 12 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein the software when executed is further configured to:
transmit, in response to the predicted demand for the one or more products, instructions to alter actions at one or more supply chain entities, the instructions comprising one or more of:
an instruction to increase capacity at one or more supply chain entity locations;
an instruction to alter product supply levels at the one or more supply chain entities;
an instruction to adjust product mix ratios at the one or more supply chain entities; and
an instruction to alter the configuration of packaging of one or more products sold by the one or more supply chain entities.

### Claim 13 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein the software when executed is further configured to:
display, on an output device, the predicted demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors.

### Claim 14 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein the software when executed is further configured to:
predict, with the second machine learning model, a third demand for the one or more products based, at least in part, on the identified one or more external causal factors, the generated one or more second price-demand elasticity causal factors, and the shaped predicted second demand for the one or more products.