Context-Aware Ad Bidding With Display-Fatigue Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advertisement bidding systems fail to account for display fatigue, leading to impatience and reduced value and efficiency in generating advertisement displays.
Innovation Solution
A method and system that adjust context-dependent parameters in bidding by tracking user display history, allocating users to groups based on display frequency, estimating marginal value per dollar spent, and modifying bidding policies to account for display fatigue, using a randomized bidding policy to optimize bids dynamically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional bidding systems place bids without accounting for future display opportunities, then bidding process is simple and fast, but the value and efficiency of advertisement displays are reduced due to display fatigue
Solution Approach 1:
The system performs preliminary analysis of user display history and fatigue levels before placing bids. By pre-calculating the impact of potential displays on future values and adjusting bids accordingly, the system avoids the need for complex real-time calculations during the bidding moment, thus improving efficiency while managing complexity
Solution Approach 2:
The bidding system dynamically adjusts bid amounts based on real-time assessment of user fatigue levels and future display opportunities. Instead of using static bid strategies, the system adapts bid parameters dynamically according to the specific user context and predicted future value, thereby improving display efficiency without requiring overly complex infrastructure
2Reliability
If bids are adjusted to account for display fatigue and future opportunities, then the value and efficiency of advertisement displays are improved, but the bidding process becomes more complex and computationally intensive
Solution Approach 1:
The system incorporates feedback loops that continuously monitor user engagement, display history, and fatigue levels. This feedback mechanism allows the system to refine bid adjustments based on actual user responses to previous displays, improving the reliability of display value while using iterative learning to manage computational complexity
Solution Approach 2:
The system changes key parameters such as bid multipliers and fatigue thresholds based on learned patterns from historical data. By adjusting these parameters dynamically rather than rebuilding complex models for each bid, the system improves display value while keeping the computational burden manageable through parameter optimization
3Measurement precision
If the system collects and analyzes extensive user display history data, then the accuracy of bid adjustments for display fatigue is improved, but the data processing requirements and system complexity increase
Solution Approach 1:
The system extracts only the most relevant features from extensive user display history data, such as frequency of displays, user engagement metrics, and fatigue indicators. By focusing on key extracted features rather than processing all raw data, the system achieves accurate bid adjustments while reducing data processing complexity and computational requirements
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems for adjusting context-dependent parameters in bidding for electronic advertisements include identifying a quantity of advertisement displays received by each of a plurality of users during a historical time period, where each user is associated with a random bidding policy. Each user is allocated to a group based upon the advertisement displays received by the user, and a marginal value per dollar spent associated with each different quantity of ad displays received by the plurality of users during the historical time period is estimated. The random bidding policy for each user is adjusted based upon the estimated marginal value per dollar spent. A bid request for an advertisement display opportunity associated with a first user is received, and a bid for the opportunity is determined based upon a characteristic of the opportunity. The determined bid is modified using the adjusted random bidding policy for the first user, and the modified bid is transmitted in response to the bid request.