# US 2023/0267484 A1 · System and methods for forecasting inventory

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

- Number: US 2023/0267484 A1
- Document ID: US20230267484A1
- Status: Published application
- Kind: A1
- Application number: 18/171,692
- Filed: 2023-02-21
- Published: 2023-08-24
- Earliest claimed: 2022-02-23
- Assignees: Jio Platforms Limited
- Applicants: Jio Platforms Limited
- Inventors: Akansha KUMAR; Manoj Reddy LAKKIREDDY; Saurabh JAIN; Athira SURENDRAN; Akhil GUPTA
- Web page: https://patentgrep.com/patent/US20230267484A1

## CPC

- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06N 20/00: Machine learning
- G06Q 10/0872: {using inventory planning}
- G06Q 10/0875: Itemisation or classification of parts, supplies or services, e.g. bill of materials
- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- G06Q 50/04: Manufacturing
- 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

A system and method for providing a robust and effective solution for forecasting inventory for a warehouse/fulfilment centre (FC) at a product batch level. The method includes calculating a demand forecast data based on a forecast algorithm, correcting the calculated demand forecast data based on one or more exogenous variable, categorizing the inventory into different buckets at a product batch level, forecasting a warehouse level inventory demand for a predefined time based on the categorization, and sending an alert to one or more users based on the categorization. The method further includes predicting a demand forecast data for one or more upcoming weeks.

## Claims

### Claim 1

A system (110) for forecasting inventory, said system (110) comprising:
one or more processors (202); and
a memory (204) operatively coupled to the one or more processors (202), wherein the memory (204) comprises processor-executable instructions, which on execution, cause the one or more processors (202) to:
estimate a demand associated with a product by calculating a demand forecast data and correcting the calculated demand forecast data;
categorize the inventory into different buckets at a product batch level based on the estimated demand; and
forecast a warehouse level inventory demand for a predefined time based on the categorization.

### Claim 2 (depends on 1)

The system (110) as claimed in claim 1, wherein the memory (204) comprises processor-executable instructions, which on execution, cause the one or more processors (202) to calculate the demand forecast data based on a forecast algorithm, and wherein the forecast algorithm comprises at least one of: an Autoregressive Integrated Moving Average Model (ARIMA), a Long short-term memory model (LSTM), an Extreme Gradient Boosting model (XGBOOST), and Holt-Winters.

### Claim 3 (depends on 1)

The system (110) as claimed in claim 1, wherein the memory (204) comprises processor-executable instructions, which on execution, cause the one or more processors (202) to correct the calculated demand forecast data based on exogenous variables, and wherein the exogenous variables comprise at least one of: local demographics, festivals, calendar, and competition.

### Claim 4 (depends on 1)

The system (110) as claimed in claim 1, wherein the memory (204) comprises processor-executable instructions, which on execution, cause the one or more processors (202) to send an alert to users based on the categorization.

### Claim 5 (depends on 1)

The system (110) as claimed in claim 1, wherein the memory (204) comprises processor-executable instructions, which on execution, cause the one or more processors (202) to estimate a future category of the current inventory based on the forecasted demand.

### Claim 6 (depends on 1)

The system (110) as claimed in claim 1, wherein the memory (204) comprises processor-executable instructions, which on execution, cause the one or more processors (202) to provide key metrics for the inventory optimization and update the key metrics periodically.

### Claim 7 (depends on 1)

The system (110) as claimed in claim 1, wherein to categorize the inventory into different buckets at the product batch level is based on Bayesian optimization.

### Claim 8

A method for forecasting inventory, said method comprising:
calculating, by a processor (202), a demand forecast data based on a forecast algorithm;
correcting, by the processor (202), the calculated demand forecast data based on one or more exogenous variables;
categorizing, by the processor (202), the inventory into different buckets at a product batch level; and
forecasting, by the processor (202), a warehouse level inventory demand for a predefined time based on the categorization.

### Claim 9 (depends on 8)

The method as claimed in claim 8, further comprising:
predicting, by the processor (202), the demand forecast data for one or more upcoming weeks.

### Claim 10 (depends on 8)

The method as claimed in claim 8, comprising sending an alert, by the processor (202), to one or more users based on the categorization.

### Claim 11

A user equipment (UE) (104) for forecasting inventory, comprising:
one or more processors; and
a memory operatively coupled to the one or more processors, wherein the memory comprises processor-executable instructions, which on execution, cause the one or more processors to:
transmit a pre-processed data comprising at least one of sales data, product data, daily inventory data, and batch level inventory data to an optimization system; and
receive an alert from the optimization system based on a categorization performed by the optimization system on the transmitted pre-processed data.
