Multi-SKU Pricing Vector Optimization for E-Commerce Conversion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Dynamic pricing methods in e-commerce often result in low traffic conversion rates due to not considering the impact on related commodities, leading to suboptimal sales and profit performance.

Innovation Solution

A pricing method that determines a price vector under test and a reference conversion rate score, adjusts prices based on comparison results, and updates current prices to improve traffic conversion rates by considering multiple SKUs as a whole, using a computer-implemented process to automatically adjust prices without manual intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual price setting by Procurement & Sales personnel is used, then pricing flexibility and business judgment are improved, but labor costs and time consumption increase

Engineering Contradiction:
Improvepricing flexibilityVSAvoidtime consumption
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system enables self-service pricing by automatically determining optimal prices for multiple SKUs based on conversion rate scores, eliminating the need for manual price setting by procurement and sales personnel while maintaining pricing flexibility through algorithmic optimization

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual pricing process with an automated computational system that calculates price vectors and conversion rate scores, substituting human judgment with algorithmic decision-making to reduce time consumption while maintaining adaptability

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If single SKU dynamic pricing is used, then individual product optimization is improved, but overall traffic conversion rate remains low

Engineering Contradiction:
Improveindividual product optimizationVSAvoidtraffic conversion rate
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The patent merges multiple individual SKU pricing decisions into a unified price vector optimization approach, where prices of multiple SKUs are adjusted together based on their interrelationships and combined impact on traffic conversion rate, achieving both individual product optimization and overall conversion rate improvement

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent transitions from one-dimensional single SKU pricing to multi-dimensional vector pricing, considering multiple SKUs simultaneously and their interactions, thereby expanding the pricing decision space to achieve better overall traffic conversion rates

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Quantity of substance

If hierarchical commodity management with multiple personnel is used, then comprehensive product coverage is improved, but system complexity and coordination overhead increase

Engineering Contradiction:
Improveproduct coverageVSAvoidsystem complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent creates a universal pricing system that handles multiple SKUs across different categories through a single automated framework, eliminating the need for separate hierarchical management structures and multiple personnel while maintaining comprehensive product coverage

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11669875B2Pricing method and device, and non-transient computer-readable storage medium
Publication Date: 2023.06.06 BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD
  • US11669875B2 patent drawing
  • US11669875B2 patent drawing
  • US11669875B2 patent drawing

AI summary

The present invention relates to the technical field of electronic commerce, and provided thereby are a pricing method performed by a computer and device, and a non-transient computer-readable storage medium. The pricing method includes: determining a price vector to be tested and a reference conversion rate score according to a set of price vectors and a conversion rate score corresponding to each price vector, wherein each price vector in the set of price vectors comprises the price of one or more inventory units in the same period; selecting an optimization direction according to a result of comparison between the conversion rate score corresponding to the price vector to be tested and the reference conversion rate score, and determining an optimized price vector on the basis of the optimization direction; and updating the current price of the inventory unit using the price in the optimized price vector.