Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Aggregate Virtual Stores for Sales Volume Optimization Engine

IP.com Disclosure Number: IPCOM000239199D
Publication Date: 2014-Oct-20
Document File: 3 page(s) / 95K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a method to improve the efficiency of current price management solutions for retail stores. The method aggregates multiple stores into one or a few virtual stores in order to reduce the problem size as well as the number of non-linear equations to be solved to reach pricing optimization.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 3

Aggregate Virtual Stores for Sales Volume Optimization Engine

A current price management solution runs optimization at store group level with

several stores defined within. A sales model is used to define price/demand relations in each store for a pre-defined product group and is a crucial part of the optimization. However, it is a non-linear econometric model, which is generally

harder to solve than its linear counterparts are. Therefore, each additional store in the model increases the size of the problem and brings along performance issues due to size and non-linearity.

The novel solution is to aggregate multiple stores into one or a few virtual stores in order to reduce the problem size as well as the number of non-linear equations to be solved. This unique modeling and approximation approach significantly reduces computation time, especially for problem settings in which the store dimension is a performance degrader.

User defines a number of virtual stores (i.e. 1 to n ). The proposed solution first groups real stores and assigns each to one abstract store. All the sales-related parameters of the real stores that belong to an abstract store are averaged to populate sales parameter values for abstract stores. Then, these abstract stores are used in an optimization step for a sales model. All other store-specific business rules are kept. All the real stores use sales volume reproduced from the associated

abstract stores.

The most obvious advantage is the reduction in computation time because optimization can use as few as one virtual store in a sales model instead of thousands in some cases. In addition, because store specific business rules are kept, pricing decisions are realistic. Because store aggre...