Performance Optimization System for Privacy-Compliant Ad Campaigns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advertising campaign optimization systems lack efficient methods to predict end user engagement and influence, especially in real-time, without relying on personally identifiable information (PII) or requiring consent in regions with strict privacy standards.
Innovation Solution
A performance optimization system (POS) that utilizes a machine learning platform to determine a POS score, which includes end user engagement metrics such as brand awareness, purchase intent, and brand consideration, by processing non-personal end user data and generating predictive models based on customer engagement data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional advertising optimization systems use PII and consent-based targeting, then they can achieve precise user targeting and engagement prediction, but they fail to comply with strict privacy regulations in certain regions
Solution Approach 1:
The patent extracts and removes personally identifiable information (PII) from the data processing pipeline while retaining non-personal characteristics that are sufficient for engagement prediction. The system processes only non-personal end user data, eliminating the need for consent mechanisms while maintaining prediction capability through anonymized behavioral patterns and contextual signals.
Solution Approach 2:
The patent introduces an intermediary layer of non-personal data processing that mediates between user privacy protection and engagement prediction needs. This intermediary mechanism uses aggregated, anonymized data and contextual information to generate predictions without directly accessing or processing identifiable user information, thus satisfying both privacy compliance and prediction accuracy requirements.
2Productivity
If real-time advertising optimization is implemented, then campaign efficiency and responsiveness are improved, but system complexity and computational requirements increase
Solution Approach 1:
The patent implements preliminary action by pre-processing and structuring non-personal data in advance, creating ready-to-use feature sets and prediction models that can be rapidly applied in real-time without requiring complex on-the-fly computations. This pre-computation approach enables fast real-time optimization while reducing the computational burden and system complexity during actual ad serving operations.
3Measurement precision
If comprehensive user data is collected for better prediction, then prediction accuracy improves, but data processing time and computational resources increase
Solution Approach 1:
The patent extracts only the essential non-personal features and characteristics needed for prediction, discarding unnecessary data elements. By selectively processing only relevant non-personal attributes rather than comprehensive user data, the system achieves accurate engagement predictions with reduced data processing time and computational resource requirements.
Data Source
AI summary
A performance optimization system (POS) includes: a POS data platform configured to store data usable to determine the POS score; a machine learning platform configured to use machine learning to determine the POS score, the machine learning platform operably connected to the POS data platform; a prediction server operably connected to the machine learning platform, the prediction server comprising a server configured to receive an advertisement request from a client demand-side platform (DSP), the prediction server further configured to create a prediction request from the advertisement request, the prediction server further configured to score the prediction request to determine a likelihood to influence an end user by exposing the end user to the brand advertisement; and a prediction request log operably connected to the prediction server, the prediction request log configured to log the scored prediction request.