Sponsored Search Result Placement Using Correlation and Quality Factors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search technologies neglect information associated with sponsored search results, leading to suboptimal placement and performance in search results pages, despite using prediction models based on bids and user behaviors.
Innovation Solution
A method and system that incorporates user behaviors, quality factors, and correlation factors to predict click likelihood and placement of sponsored search results, using machine learning models to determine the most appropriate placement on search results pages, enhancing user experience and revenue for publishers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If prediction models based on bids and user behaviors are used to determine sponsored search results placement, then relevance of sponsored search results to search keywords is improved, but information associated with sponsored search results themselves is neglected causing performance bottleneck
Solution Approach 1:
The patent changes the parameters used in prediction models from solely bid and user behavior data to include quality factors specific to sponsored search results (such as ad relevance, expected CTR, and landing page quality). This parameter expansion allows the system to capture and utilize previously neglected information about the sponsored results themselves, resolving the bottleneck in performance while maintaining relevance to search keywords.
2Manufacturing precision
If multiple quality factors are considered for sponsored search results, then placement accuracy is improved, but system complexity increases
Solution Approach 1:
The patent segments the quality assessment into distinct factors (ad relevance, expected CTR, landing page quality) that can be evaluated independently. Each factor can be processed by separate modules or algorithms, making the overall system more manageable and easier to optimize. This segmentation allows high placement accuracy through multi-factor consideration while controlling system complexity through modular architecture.
Solution Approach 2:
The system performs preliminary evaluation and scoring of quality factors before final placement determination. By pre-calculating and ranking sponsored search results based on quality factors, the system simplifies the final placement decision process. This preliminary action reduces the computational burden during placement and makes the complex multi-factor evaluation more efficient.
Data Source
AI summary
The present teaching relates to placing sponsored search results based on correlation of the sponsored search results. A search query is first received at a search engine from a user. One or more keywords are further extracted from the search query. A plurality of sponsored search results related to the one or more keywords are received in response to the search query. The placement of the plurality of sponsored search results are further determined based on correlation of the plurality of sponsored search results, and a search results page containing the plurality of sponsored search results are presented to the user.