Latency Reduction in Feedback-Based Performance Determination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Content providers face challenges in predicting the performance of content item objects, such as application installations, due to latency in feedback-based system performance determination, especially when rendering on various web properties and networks, making it difficult to configure effective content campaigns.
Innovation Solution
A data processing system that uses improved tracking interfaces and statistical modeling techniques, including machine learning and multivariable regression, to provide real-time performance estimates by merging internal data with data from application developers, allowing for accurate prediction of application installations and in-application events based on input values like bids, budgets, and geographic locations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If feedback-based system performance determination is used to track application installations and in-application events, then measurement precision is improved, but loss of time increases due to latency in receiving and processing feedback data
Solution Approach 1:
The system performs preliminary actions by collecting and storing feedback data from tracking interfaces in advance, merging it with event data before performance determination is needed. This pre-processing approach reduces the time required for actual performance calculation while maintaining measurement precision.
Solution Approach 2:
A data processing system acts as an intermediary between tracking interfaces and performance determination processes. This intermediary collects, merges, and pre-processes data from multiple sources (tracking interfaces, event data, configuration data), thereby reducing the computational burden and time required for final performance determination.
2Productivity
If real-time performance prediction is implemented by merging internal data with external ping data, then productivity is improved through faster decision-making, but device complexity increases due to multiple data sources and processing requirements
Solution Approach 1:
The data processing system performs multiple functions: collecting data from tracking interfaces, merging with event data, validating configuration data, and generating performance predictions. This multi-functional approach consolidates what would otherwise require separate systems, managing complexity while enabling real-time productivity improvements.
Solution Approach 2:
The system automatically merges and processes data from multiple sources without requiring manual intervention. The data processing system self-manages the complexity of integrating internal and external data sources, performing validations, and generating predictions, thereby improving productivity while containing complexity within the automated system.
3Measurement precision
If comprehensive data merging is performed to generate accurate performance predictions, then measurement precision is improved, but loss of time increases due to extensive data processing requirements
Solution Approach 1:
The system performs preliminary data merging and validation operations in advance, combining internal event data with external ping data before performance prediction is needed. This pre-processing approach ensures measurement precision is maintained while reducing the time required for actual prediction generation.
Solution Approach 2:
The data processing system serves as an intermediary that handles the complex task of merging comprehensive data from multiple sources. By centralizing this data processing function, the system achieves high measurement precision through thorough data integration while managing processing time through dedicated optimization of the intermediary processing layer.
Data Source
AI summary
The present disclosure is directed to a technique to reduce latency in feedback-based system performance determination. A system receives, from an application developer device, indications of an in-application event and a first input value for an application content delivery profile. The system receives, via an interface from an application developed by an application developer and executed by a computing device remote from the data processing system and different from the application developer device, a ping indicative of an occurrence of the in-application event on the computing device. The system merges data from the ping with internal data determined by the data processing system to generate merged data. The system determines a predicted performance for the in-application event and provides an indication of the predicted performance. The system configures, responsive to the indication of the predicted performance, the application content delivery profile with a second input value.