Content Item Expansion Prediction Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting the expansion direction of expandable content items, such as advertisements, on web pages often result in distortion or failure to expand properly, leading to a poor user experience and reduced monetization opportunities for publishers.
Innovation Solution
A method that identifies a predicted expansion direction for content item environments based on the display configuration of the resource, generates a serving data log entry, and receives reporting messages to determine accuracy measures, allowing for adjustments to improve prediction accuracy and prevent distortion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If expandable content items are provided to user devices for display in content item environments, then monetization opportunities for publishers are increased, but distortion or failure to expand properly occurs leading to poor user experience
Solution Approach 1:
The system performs preliminary analysis of the resource display configuration and content item environment characteristics before serving expandable content items. It predicts the expansion direction based on pre-collected data about the resource layout, content item position, and available expansion space, ensuring the content item can expand properly without distortion.
Solution Approach 2:
The system collects feedback data from user devices regarding actual expansion outcomes and uses this information to refine and update the prediction model. By continuously learning from real-world expansion results, the system improves its prediction accuracy over time, reducing distortion and failure cases.
2Measurement precision
If predicted expansion direction is determined based on resource address, then expansion accuracy is improved, but data collection and processing complexity increases
Solution Approach 1:
The system uses a universal data collection approach where the same tracking infrastructure serves multiple purposes: it collects resource display configuration data, content item environment characteristics, user interaction information, and expansion outcome feedback. This multi-functional data collection reduces overall system complexity compared to separate specialized systems.
Solution Approach 2:
The system leverages existing web page metadata, display configuration data, and resource information that are already available or easily obtainable from the resource itself. By using self-describing data from the resource (such as layout information, content item positions, and expansion parameters), the system reduces the need for complex external data collection infrastructure.
Data Source
AI summary
Methods, and systems, including computer programs encoded on computer-readable storage mediums, including a method for determining accuracy measures for predicted expansion directions for content item environments. The method includes, identifying a predicted expansion direction for the content item environment; generating a serving data log entry for the request specifying the predicted expansion direction and a unique identifier for the request; providing an expandable content item having the predicted expansion direction and response data specifying the unique identifier; receiving reporting messages specifying the display configurations of the resources and content item environments; determining pairs of serving data log entries and reporting messages based on the unique identifiers, each pair having a matching unique identifier; and determining an accuracy measure for the respective predicted expansion direction based on a comparison of the respective predicted expansion direction and the display configurations of the respective resource and content item environment.