Ecommerce Search Ranking via Query-Price Affinity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ecommerce search systems often display items with significantly varying prices, leading to reduced user engagement as items outside the typical price range may be less relevant to the customer's query, resulting in accessories being prioritized over the intended item.
Innovation Solution
A result ranking system that determines a feature value for each item based on customer interaction data, using a query-price affinity function to rank items within a typical price range, thereby prioritizing items closer to the average price and reducing the visibility of out-of-range items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If search systems return items based exclusively on query string relevance, then search simplicity is maintained, but user engagement decreases due to price-related irrelevance
Solution Approach 1:
The patent modifies the search ranking parameters by introducing price as an additional sorting criterion. The system calculates a price relevance score based on the relationship between item price and query terms, then integrates this score into the overall ranking algorithm. This allows the system to maintain query-based simplicity while improving user engagement through price-aware result ordering.
2Adaptability or versatility
If search systems display items with varying price ranges, then search comprehensiveness is improved, but user engagement reduces due to display of less relevant items
Solution Approach 1:
The patent applies local quality by differentiating the treatment of items based on their price characteristics. The system calculates price relevance scores for each item and uses these scores to adjust ranking positions selectively. Items with prices that align better with query intent receive higher rankings, while items with mismatched prices are downgraded. This localized differentiation maintains comprehensiveness while improving engagement by reducing visibility of clearly irrelevant items.
3Quantity of substance
If search systems prioritize items outside typical price range, then search coverage is expanded, but user engagement decreases due to display of accessories instead of main items
Solution Approach 1:
The patent introduces price relevance score as an intermediary factor between query matching and final result ranking. This intermediary component analyzes the relationship between item price and query terms, producing a relevance score that mediates the final positioning. The system uses this intermediary score to adjust rankings, ensuring that items like accessories with significantly different price points are downgraded in favor of main items with more aligned price expectations, thereby improving engagement while maintaining search coverage.
Data Source
AI summary
A result ranking system can include a computing device that is configured to obtain a plurality of items based on a query and a value corresponding to each item of the plurality of items. The computing system can also be configured to retrieve a value distribution corresponding to the query and generated based on customer interaction data. The computing system can also, for each item of the plurality of items, determine a feature value based on the value distribution and the corresponding value of the item. The computing system can be further configured to transmit the plurality of items to a customer device for display in an arrangement based on the corresponding feature value.