Substitutable Item Demand Planning with Linear Elasticity Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing demand planning models for retail forecasting are inefficient and impractical due to the quadratic scaling of cross elasticity calculations for numerous products, leading to unreliable and incomplete data, which fails to account for 90% of item interactions, and are not scalable for large retail environments.
Innovation Solution
A demand planning model that calculates cross elasticity for each item and a single category elasticity, reducing calculations to linear scalability (n+1) and incorporating linear programming for optimized pricing, allowing for accurate forecasting of sales and item interactions without estimating cross elasticities for every pair.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cross elasticity is calculated for every pair of substitutable items, then measurement precision of demand relationships is improved, but device complexity and computational burden increase quadratically
Solution Approach 1:
The patent segments the demand relationship analysis into two parts: (1) individual item-level elasticities that capture direct price-demand relationships, and (2) category-level aggregate elasticity that captures substitutable item interactions. This segmentation avoids the need to calculate cross elasticity for every item pair while preserving measurement precision through the category-level aggregation approach.
Solution Approach 2:
The patent merges individual item elasticities into a category-level aggregate elasticity that represents the combined effect of substitutable items. By combining these measurements at the category level rather than maintaining separate item-pair measurements, the system achieves comprehensive demand relationship accuracy with linear computational complexity instead of quadratic.
2Reliability
If cross elasticity calculations are performed for all item pairs, then reliability of demand forecast is improved, but productivity and scalability deteriorate
Solution Approach 1:
The forecasting system segments the analysis into item-level and category-level components, calculating only n+1 elasticity values instead of O(n²) item-pair values. This segmentation maintains forecast reliability by capturing essential substitutable item interactions through category-level aggregation while dramatically improving productivity through linear scalability.
Solution Approach 2:
The patent applies partial action by calculating only the necessary elasticity measurements (individual item elasticities and category-level aggregate) rather than performing complete cross elasticity calculations for all item pairs. This partial measurement approach is sufficient to achieve reliable demand forecasts while maintaining high forecasting efficiency and scalability.
3Loss of information
If complete cross elasticity data is collected, then loss of information is reduced, but device complexity and data processing requirements increase
Solution Approach 1:
The patent merges individual item elasticity data into category-level aggregate elasticity that captures the combined interaction effects of substitutable items. This merging approach reduces information loss by preserving category-level substitution patterns while avoiding the need to process and store complex item-pair cross elasticity data, thereby reducing data processing complexity.
Solution Approach 2:
The patent extracts only the essential elasticity measurements needed for accurate demand forecasting: individual item elasticities and category-level aggregate elasticity. By extracting and discarding redundant item-pair cross elasticity calculations, the system minimizes information loss while significantly reducing data processing complexity and storage requirements.
Data Source
AI summary
A system and method are disclosed for planning a product assortment based on a sales forecast without using a cross elasticity by receiving a percentage pricing change for at least two substitutable products of an inventory in a supply chain network having one or more supply chain entities, and at least two substitutable products are grouped in the same product category and at least one of at least two substitutable products is grouped in a product assortment, calculating an average percent pricing change for the product category including at least two substitutable products and a direct effect factor and cross-effect factor for each of at least two substitutable products, and identifying an item of at least two substitutable items to be removed from the product assortment based, at least in part, on a substitutable demand calculated by modeling a price increase of a substitutable item to infinity.