Automated Bidding System Using Aggregate Model Modules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search-marketing campaigns lack real-time analytics and efficient metrics to fine-tune bids on target keywords, leading to inefficiencies and high bidding prices due to reliance on long-term metrics and proprietary data from search engines with vested interests.
Innovation Solution
An automated bidding system utilizing an aggregate model with multiple modules to predict and adjust marketing indicators, determining a bid value based on real-time data comparison and historical trends, allowing for dynamic optimization of search engine rankings and cost per click.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fixed, long-term time scales are used for metrics and analytics, then data availability is improved, but real-time responsiveness and fine-tuning capability deteriorate
Solution Approach 1:
The patent implements dynamic time scaling where the system automatically adjusts the time window for data aggregation based on campaign performance and user behavior patterns. Instead of fixed long-term metrics, the system uses rolling windows that can contract to capture real-time trends or expand for stable baseline measurements, resolving the contradiction between data reliability and real-time responsiveness
Solution Approach 2:
The patent segments the metrics system into multiple parallel tracks: real-time event tracking for immediate responsiveness, short-term aggregation windows for tactical adjustments, and long-term trends for strategic planning. This segmentation allows the system to maintain reliable data availability across different time horizons simultaneously without sacrificing real-time capability
2Loss of information
If proprietary metrics from search engines are used, then data completeness is improved, but independence and cost efficiency deteriorate
Solution Approach 1:
The patent introduces an intermediary layer of event tracking and data collection that operates independently of search engine proprietary metrics. This intermediary system captures raw user interaction data directly from the website and application, creating an independent data source that can be processed and analyzed without reliance on external proprietary systems, thereby maintaining data completeness while ensuring independence
Solution Approach 2:
The patent implements feedback loops where the system continuously compares proprietary search engine metrics with independently collected event tracking data. This feedback mechanism validates the independence of the measurement system while ensuring that no critical information is lost by identifying and reconciling discrepancies between the two data sources
3Measurement precision
If manual bid adjustment processes are used, then control precision is improved, but operational efficiency and responsiveness deteriorate
Solution Approach 1:
The patent implements self-service automation where the system automatically monitors performance metrics, analyzes trends, and adjusts bid values without manual intervention. The system uses predefined optimization rules and machine learning models to make precise bid adjustments autonomously, maintaining control precision while dramatically improving operational efficiency and responsiveness to market changes
Solution Approach 2:
The patent replaces the mechanical manual bid adjustment process with an automated computational system that uses algorithms and data analysis to determine optimal bid values. This substitution eliminates the time-consuming manual process while maintaining or improving control precision through more sophisticated and consistent decision-making logic
4Measurement precision
If high bidding prices are used, then search engine ranking visibility is improved, but cost efficiency deteriorate
Solution Approach 1:
The patent implements dynamic bid pricing that continuously adjusts bid values based on real-time performance data, competition levels, and predicted user behavior. Instead of using consistently high bids to maintain visibility, the system optimizes bid amounts dynamically, increasing bids only when expected to generate positive ROI and reducing bids when performance is suboptimal, thereby maintaining ranking visibility while improving cost efficiency
Data Source
AI summary
A computer-implemented method may include predicting a first marketing indicator using a first module of an aggregate model; comparing the predicted first marketing indicator with a measured first marketing indicator; and based on the comparison of the predicted first marketing indicator with the measured first marketing indicator, adjusting the first module of the aggregate model. Additionally, the method may include predicting a second marketing indicator using a second module of the aggregate model; comparing the predicted second marketing indicator with a measured second marketing indicator; and based on the comparison of the predicted second marketing indicator with the measured second marketing indicator, adjusting the second module of the aggregate model. Further, the method may include determining a bid value based on the aggregate model.