Item Ranking Algorithm for Advertisement Relevance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing digital advertisement systems often display irrelevant item advertisements to customers, leading to lost sales opportunities for retailers as customers may not engage with or purchase advertised items, resulting in reduced revenue and customer dissatisfaction.

Innovation Solution

A computing device determines and ranks item advertisements based on relevance to an anchor item, incorporating sponsored items with cost values, to provide more relevant and engaging advertisements on websites, thereby improving customer experience and increasing advertisement conversions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If traditional advertisement systems display sponsored items without relevance filtering, then advertiser revenue is maximized, but customer engagement and purchase conversion decrease

Engineering Contradiction:

Improvecustomer engagement timeVSAvoidadvertisement conversion rate

Core Design Contradiction:

Loss of energyVSProductivity

Solution Approach 1:

The patent applies local quality by determining relevance scores for individual advertisements relative to the anchor item and customer context. Each advertisement is evaluated and ranked based on its specific relevance to the current shopping context, rather than treating all advertisements uniformly. This allows the system to prioritize highly relevant ads while filtering out irrelevant ones, improving both customer engagement and conversion rates.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes the parameter of advertisement selection from purely sponsored bid-based ranking to relevance-based ranking. By introducing relevance scores as a new parameter and using them to determine advertisement display priority, the system transforms the advertisement selection process to balance advertiser revenue with customer interest, thereby improving engagement and conversion.

Inventive Principle:

Principle #35Parameter changes

2Quantity of substance

If irrelevant advertisements are displayed to maximize ad inventory utilization, then advertisement volume increases, but customer satisfaction and site retention decrease

Engineering Contradiction:

Improvenumber of advertisements displayedVSAvoidcustomer satisfaction

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The patent changes the selection parameter from quantity-focused to quality-focused by introducing relevance scores. Instead of displaying maximum number of advertisements, the system displays advertisements ranked by their relevance to the anchor item and customer context, ensuring that the advertisements shown are both numerous enough to maintain inventory utilization and relevant enough to satisfy customers.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system uses feedback mechanisms by analyzing customer interactions with advertisements and adjusting relevance rankings accordingly. By monitoring which advertisements receive engagement and which are ignored, the system continuously refines its relevance determination, ensuring that displayed advertisements maintain high customer satisfaction while preserving adequate advertisement volume.

Inventive Principle:

Principle #23Feedback

3Productivity

If sponsored advertisements are prioritized without relevance consideration, then advertiser revenue is optimized, but retailer sales opportunities are lost

Engineering Contradiction:

Improveadvertiser revenueVSAvoidpotential sales revenue

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The patent introduces relevance scores as a new parameter that modifies the traditional sponsored advertisement ranking system. Instead of ranking solely by bid amount, the system ranks advertisements by relevance score, ensuring that sponsored items that are actually relevant to the customer and anchor item are prioritized. This balances advertiser revenue optimization with retailer sales opportunity preservation.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The relevance score acts as an intermediary between advertiser revenue goals and retailer sales objectives. By using relevance scores to mediate the selection process, the system ensures that sponsored advertisements that have both revenue potential and customer relevance are selected, thereby simultaneously optimizing advertiser revenue and protecting retailer sales opportunities.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11551261B2Methods and apparatus for electronically determining item advertisement recommendations

Publication Date: 2023.01.10 WALMART APOLLO LLC

AI summary

This application relates to apparatus and methods for automatically determining and providing, for a given anchor item, a ranking of items. The ranking may include sponsored items. In some examples, a computing device receives a request for items for an anchor item. The computing device determines a relevancy of a plurality of recommended items and sponsored items. The computing device also determines a cost value for the sponsored items. The computing device determines ranking values for the plurality of recommended items and sponsored items based on the relevancy values and the cost values, and ranks the items based on the ranking values. In some examples, the computing device updates the final item ranking based on the application of one or more rules. The computing device transmits the final item ranking to a web server. The web server displays advertisements for the items in ranked order.