Dynamic Bidding Rule Generation Using ML Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating electronic bid values for digital content objects are inefficient and inaccurate due to reliance on static rules and lack of consideration for additional attributes associated with device rendered objects, leading to mismanagement of resources and suboptimal performance.
Innovation Solution
A predictive dynamic bidding rule generation system that uses a machine learning model to cluster digital content objects based on similarities and adjust electronic bid values dynamically, incorporating device rendered object attributes, interaction currency values, and timestamps to optimize bidding strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If static rules are used for generating electronic bid values, then the bidding process is simple to implement, but the accuracy and performance of bid values deteriorate
Solution Approach 1:
The patent transitions from static bidding rules to dynamic bid adjustment rules that automatically adapt to changing conditions. The system continuously monitors device rendered object attributes, interaction currency values, and timestamps, then dynamically adjusts electronic bid values based on machine learning model predictions, allowing the bidding strategy to evolve with real-time data while maintaining automated operation.
2Measurement precision
If additional attributes and real-time data are incorporated into bid generation, then the accuracy of bid values improves, but the computing resources and time required increase
Solution Approach 1:
The patent segments the bid adjustment process by clustering digital content objects into groups based on shared attributes and performance characteristics. The machine learning model processes data in organized segments (clusters) rather than individually for each digital content object, reducing computational complexity while maintaining accuracy. This segmentation allows efficient processing of device rendered object attributes, interaction currency values, and timestamps.
Solution Approach 2:
The system performs preliminary actions by pre-processing and organizing device rendered object data, attributes, and interaction history before bid generation. The machine learning model is trained in advance on historical data to establish patterns and relationships, enabling faster real-time bid adjustments without requiring intensive computing resources during actual bidding operations.
3Adaptability or versatility
If device rendered object attributes and interaction data are analyzed, then the relevance and effectiveness of bidding strategies improve, but the complexity of the system increases
Solution Approach 1:
The patent introduces a machine learning model as an intermediary between raw device rendered object data and bid adjustment decisions. The model acts as a mediator that automatically processes complex attributes, interaction currency values, and timestamps, translating them into actionable bid adjustments without requiring manual system configuration. This intermediary handles the complexity internally while presenting a simplified interface for bid management.
Solution Approach 2:
The system implements self-service through automated bid adjustment rules that independently analyze device rendered object attributes, interaction data, and performance metrics. The machine learning model autonomously identifies patterns and generates bid adjustments without human intervention, allowing the system to adapt to changing conditions while managing its own complexity through self-learning and automatic optimization.
Data Source
AI summary
Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products for predictive dynamic bidding rules generation for digital content objects.