Electronic Planogram Generation Using Regression Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer models for generating electronic planograms are inefficient and inaccurate, failing to effectively correlate space and sales relationships for item categories, leading to suboptimal shelf space allocation and reduced profit in retail environments.
Innovation Solution
A system and method using constrained linear regression models for calculating space elasticity, multiple non-linear regression models for cross-space elasticity, and non-linear multiple-constraint mixed integer optimization models to generate optimal category space allocations, resulting in improved electronic planograms that maximize revenue.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If existing computer models are used for generating electronic planograms, then the generation process can be automated, but the models are inefficient and inaccurate in correlating space and sales relationships
Solution Approach 1:
The patent transforms the planogram generation problem by changing the mathematical parameters and models used. It employs advanced regression models (elasticity models, gravity models, multinomial logit models) that incorporate multiple parameters including space elasticity, cross-space elasticity, category interactions, and substitution effects. These parameter changes enable accurate correlation between space allocation and sales performance while maintaining full automation of the generation process.
2Reliability
If shelf space is allocated to maximize total profits, then revenue can be increased, but the allocation of limited shelf space among different item categories becomes more complex
Solution Approach 1:
The patent segments the shelf space allocation problem into distinct mathematical components: space elasticity calculations for individual categories, cross-space elasticity for category interactions, and substitution effects. By dividing the complex allocation problem into these separable mathematical segments that can be calculated and optimized independently before being combined, the system achieves profit maximization while managing computational complexity through structured decomposition.
3Extent of automation
If a computer system manages shelf space with inefficient models, then automation is provided, but the system runs inefficiently and produces suboptimal results
Solution Approach 1:
The patent replaces inefficient mechanical/computational models with advanced mathematical and statistical models. It substitutes traditional simple allocation methods with elasticity-based regression models, gravity models, and optimization algorithms that accurately capture consumer behavior, category interactions, and substitution effects. This substitution dramatically improves the productivity and efficiency of the computerized shelf space management system while maintaining full automation.
Data Source
AI summary
Systems and methods for generating an electronic planogram optimized for space elasticity calculating a space elasticity include training a constrained linear regression model using a first training dataset, training a multiple non-linear regression model based on a second training dataset including, training a non-linear multiple-constraint mixed integer optimization model based at least in part on an output of the constrained linear regression model and an output of the multiple non-linear regression model, and generating an electronic planogram optimized for space elasticity. For each item category, a space elasticity is determined by fitting the constrained linear regression model, the multiple non-linear regression model is applied to determine a cross-space elasticity, and the non-linear multiple-constraint mixed integer optimization model generates a category space allocation. The category space allocation for each item category is aggregated to generate the electronic planogram. The electronic planogram is validated based on received sales data.