Method and system for managing clearance markdown

Patent metadata

Field	Value
Publication number	US-2024303680-A1
Application number	US-202318182250-A
Country	US
Kind code	A1
Filing date	Mar 10, 2023
Priority date	Mar 10, 2023
Publication date	Sep 12, 2024
Grant date	—

Abstract

Methods and systems for creation and management of a clearance schedule for in-store clearance of a retail item are disclosed. A markdown schedule may be generated using a first model representing a demand forecast and a second model that represents estimated price elasticity for the item to be placed into the clearance program. The estimated price elasticity may be determined from historical sales data of an identified past clearance item. In some instances, backtesting data may be generated from past clearance sales, and a comparison of the backtesting data to the current clearance program may be performed to update the markdown schedule. In some instances, updated sales data may be received, and model parameters updated. A user interface presenting a revised demand forecast may be generated, and a clearance schedule implementation tool may update the optimal markdown schedule for the inventory item for future periods of the clearance program.

First claim

What is claimed is:

1 . A method for managing an inventory item for in-store clearance, the method comprising:
receiving, at a clearance schedule tool, a selection of an inventory item for clearance; accessing, at the clearance scheduling tool, historical sales data for the inventory item for a predetermined time period before a start of a clearance program; using the historical sales data, identifying a demand local maxima for the inventory item; based on the demand local maxima, filtering the historical sales data to include data between the demand local maxima and the start of the clearance program; based on the filtered historical sales data, building a first model that represents a demand forecast for the inventory item during the clearance program; generating a continuous time series representing the demand forecast for the inventory item during the clearance program as determined using the first model; sending instructions to the clearance schedule implementation tool to implement an optimal markdown schedule for the inventory item based on the demand forecast for the inventory item during the clearance program; dynamically receiving, at the clearance schedule tool, updated sales data for the inventory item during the clearance program, wherein the clearance schedule tool includes an automated feedback dataflow that continuously accesses sales data for the inventory item during the clearance program and receives updates based on changes to sales data; in response to receiving updated sales data, updating at least one parameter of the first model; outputting, on the user interface, a revised continuous time series representing a revised demand forecast for the inventory item during the clearance program as determined using the first model with the updated at least one parameter; and sending instructions to the clearance schedule implementation tool to implement an updated optimal markdown schedule for the inventory item based on the revised demand forecast for the inventory item during the remainder of the clearance program.

2 . The method of claim 1 , wherein building the first model comprises:
splitting the filtered historical sales data into training data and testing data; using the training data to calculate optimal values for parameters of the first model; and in response to calculating optimal values for parameters of the first model, testing the first model with the testing data.

3 . The method of claim 2 , wherein the historical sales data is weekly sales data and the testing data includes the last two values of the filtered historical sales data before the start of the clearance program.

4 . The method of claim 1 , wherein the parameters of the first model include a dynamic trend factor, a smoothing factor, and a damping factor.

5 . The method of claim 1 , further comprising:
applying a second model that represents an estimated price elasticity for the inventory item for clearance to the first model.

6 . The method of claim 1 , further comprising:
generating a set of possible markdown schedules for the inventory item for clearance, each possible markdown schedule of the set defining a set of prices and associated price durations; and in response to outputting the revised continuous time series, generating an updated set of possible markdown schedules.

7 . The method of claim 1 , wherein the clearance program is an in-store clearance program.

8 . The method of claim 1 , further comprising:
aggregating the historical sales data at an item cluster level; and in response to sending instructions to the clearance schedule implementation tool to implement the optimal markdown schedule, disaggregating the historical sales data from an item cluster level to an item store level.

9 . The method of claim 1 , further comprising:
concurrently displaying, on the user interface, a graphical representation of the continuous time series and the revised continuous time series.

10 . The method of claim 1 , further comprising:
comparing the continuous time series and the revised continuous time series to calculate a weekly error rate.

11 . The method of claim 1 , further comprising:
saving the continuous time series and the revised continuous time series in a database accessible by the clearance schedule tool and the clearance implementation tool.

12 . The method of claim 1 , wherein updated sales data for the inventory item is automatically received weekly during the clearance program.

13 . A system for managing an inventory item for clearance, the system comprising:
a computing system including a processor, and a memory communicatively coupled to the processor, the memory storing instructions executable by the processor to:
receive, at a clearance schedule tool, a selection of an inventory item for clearance;
access, at the clearance scheduling tool, historical sales data for the inventory item for a predetermined time period before a start of a clearance program;
using the historical sales data, identify a demand local maxima for the inventory item;
based on the demand local maxima, filter the historical sales data to include data between the demand local maxima and the start of the clearance program;
based on the filtered historical sales data, build a first model that represents a demand forecast for the inventory item during the clearance program;
output, on a user interface having a selectable feature configured to launch a downstream clearance schedule implementation tool, a continuous time series representing the demand forecast for the inventory item during the clearance program as determined using the first model;
send instructions to the clearance schedule implementation tool to implement an optimal markdown schedule for the inventory item based on the demand forecast for the inventory item during the clearance program;
dynamically receive, at the clearance schedule tool, updated sales data for the inventory item during the clearance program, wherein the clearance schedule tool includes an automated feedback dataflow that continuously accesses sales data for the inventory item during the clearance program and receives updates based on changes to sales data;
in response to receiving updated sales data, update at least one parameter of the first model;
output, on the user interface, a revised continuous time series representing a revised demand forecast for the inventory item during the clearance program as determined using the first model with the updated at least one parameter; and
send instructions to the clearance schedule implementation tool to implement an updated optimal markdown schedule for the inventory item based on the revised demand forecast for the inventory item during the remainder of the clearance program.

14 . The system of claim 13 , wherein the instructions stored in the memory cause the system to build the first model by:
splitting the filtered historical sales data into training data and testing data; using the training data to calculate optimal values for parameters of the first model; and in response to calculating optimal values for parameters of the first model, testing the first model with the testing data.

15 . The system of claim 13 , wherein the historical sales data is weekly sales data and the testing data includes the last two values of the filtered historical sales data before the start of the clearance program.

16 . The system of claim 13 , wherein the instructions stored in the memory are further executable by the process to:
apply a second model that represents an estima

Assignees

• Target Brands Inc

Inventors

• Shukla Aishwarya
• Kalsi Nishant
• Yaddula Narendra
• Pal Gayatri
• S Vivek

Classifications

• G06Q10/06315

  Needs-based resource requirements planning or analysis · CPC title

• G06Q10/087

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• G06Q30/0202

  Market predictions or forecasting for commercial activities · CPC title

• G06Q30/0206 Primary

  Price or cost determination based on market factors · CPC title