Promotion Price Optimization via Automated Vehicle Assignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Retailers face difficulties in setting promotion prices for multiple products while balancing profitability and revenue generation, especially when faced with numerous items that require pricing during promotional events.
Innovation Solution
A computer-implemented system and method that uses an optimizer to determine optimal promotion prices and vehicle assignments for items, considering demand models, nonlinear effects, and business constraints, employing local searching instructions and branching schemes to compute incremental changes in performance indexes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual pricing methods are used for multiple products during promotion events, then pricing decisions can be made with business rule constraints, but the complexity and time required increases significantly with the number of items
Solution Approach 1:
The patent replaces manual pricing mechanisms with an automated computer-implemented optimization system. The optimizer uses mathematical formulations and algorithms to automatically determine promotion prices and vehicle assignments, eliminating the need for manual pricing decisions while handling complex constraints and multiple products simultaneously.
Solution Approach 2:
The system enables self-service pricing optimization where the optimizer autonomously analyzes product data, demand models, and business rules to generate optimal pricing recommendations without requiring manual intervention for each product. The system serves itself by automatically processing and optimizing pricing for all items in the catalog.
2Productivity
If promotion prices are reduced to generate revenue and profit, then sales volume increases, but the profitability per item decreases
Solution Approach 1:
The optimizer dynamically adjusts pricing parameters by analyzing demand elasticity and cross-effects between products. It determines optimal promotion prices that balance price reductions with profitability by considering how price changes affect both own-demand and cross-demand, ensuring that price cuts are optimized to maximize overall profit rather than simply increasing volume.
Solution Approach 2:
The system incorporates demand models that provide feedback on how pricing decisions affect product demand. The optimizer uses this feedback to iteratively refine pricing recommendations, considering the impact of price changes on both individual product sales and overall portfolio profitability, allowing for data-driven optimization of the price-profit balance.
3Measurement precision
If optimization formulations consider nonlinear demand models and cross effects on demands, then pricing accuracy improves, but the computational complexity and processing time increases
Solution Approach 1:
The system performs preliminary actions by pre-processing product data, organizing it into structured formats, and preparing demand models before optimization execution. This preliminary organization of data and constraints enables the optimizer to efficiently process complex nonlinear models without excessive computation time during the actual optimization run.
4Adaptability or versatility
If the system handles large-scale promotion scenarios with thousands of items and locations, then comprehensive coverage is achieved, but the computational burden and processing requirements increase
Solution Approach 1:
The system segments the large-scale optimization problem into manageable components by organizing products, locations, and constraints into structured data formats. The optimizer processes the catalog in an organized manner, breaking down the complex large-scale problem into smaller sub-problems that can be solved efficiently while maintaining overall optimization goals.
Data Source
AI summary
Computer-implemented systems and methods for determining promotion prices for a plurality of items. A system and method can be configured to receive electronic data about items for a promotion event and to receive electronic data about vehicles for a promotion event. An optimizer, which is implemented on a data processor, includes or has access to an optimization formulation for determining optimal promotion prices for the items and for determining assignments of the vehicles to the items for promoting the items during the promotion event.