Ad Campaign Pacing via Interval Scaling Filters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional online advertising methods struggle to effectively pace the presentation of advertisements over a specified time limit, leading to premature exhaustion of campaign budgets and incomplete achievement of advertising objectives due to unpredictable user engagement and varying bid amounts.
Innovation Solution
A social networking system modifies the inclusion of advertisements in auctions by determining interval objectives and using scaling filters to regulate the number of impressions and reach throughout the campaign duration, ensuring objectives are met by adjusting bid amounts and inclusion probabilities based on performance data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional advertisement selection methods are used, then advertisements are presented based on user eligibility and bid amounts, but the budget is exhausted prematurely and advertising objectives are not achieved over the full campaign duration
Solution Approach 1:
The patent applies dynamics by making the advertisement selection process adaptive rather than static. The system dynamically adjusts the probability of selecting advertisements from different campaigns based on real-time performance data, remaining budget, and time elapsed. This allows the system to respond to changing conditions and distribute impressions evenly across the campaign duration, preventing premature budget exhaustion while maintaining productivity.
Solution Approach 2:
The patent implements feedback mechanisms by continuously monitoring advertising campaign performance, including impressions delivered, budget spent, and time elapsed. This feedback is used to adjust future advertisement selection probabilities, ensuring that campaigns stay on track to meet their objectives within the specified duration. The system learns from past performance and modifies its behavior accordingly.
2Quantity of substance
If advertisements are selected based on user eligibility and bid amounts, then high-bid advertisements are presented frequently, but the budget is exhausted too quickly and lower-bid advertisements do not receive sufficient impressions
Solution Approach 1:
The patent changes the selection parameters from purely bid-based to a composite model that includes bid amount, campaign performance metrics, remaining budget, and time elapsed. This parameter transformation allows the system to balance between high-bid and lower-bid advertisements, distributing impressions more evenly over time while still favoring higher-performing campaigns. The modified selection criteria prevent premature budget exhaustion.
Solution Approach 2:
The system dynamically adjusts advertisement selection probabilities based on real-time conditions. As campaigns progress and budget decreases, the system adapts its selection criteria to ensure objectives are met within the remaining time. This dynamic adjustment prevents both premature budget exhaustion and ensures sufficient impressions are delivered to all campaigns.
3Ease of operation
If the number of eligible users fluctuates unpredictably, then advertisement presentation varies, but the advertiser cannot regulate or predict advertisement distribution throughout the campaign
Solution Approach 1:
The patent uses feedback from actual user eligibility and advertisement presentation data to adjust selection probabilities. By monitoring what actually happens in the system and comparing it to campaign objectives, the advertiser gains control over the distribution pattern. The system compensates for unpredictable user fluctuations by adjusting selection criteria based on observed performance and remaining resources.
Solution Approach 2:
The patent introduces an intermediary layer (the modified selection system) between user eligibility and advertisement presentation. This intermediary processes and smooths out the fluctuations in eligible user numbers by using a probabilistic selection model that considers multiple factors including remaining budget and time. This mediator allows advertisers to regulate distribution even when underlying user eligibility varies unpredictably.
Data Source
AI summary
An advertiser specifies an advertising campaign along with a budget, a duration and one or more objectives associated with the advertising campaign. An online system presenting advertisements from the advertising campaign determines an interval representing a portion of the duration, an interval budget, and one or more interval objectives. Historical information describing selection and presentation of advertisements by the online system is retrieved, and used to determine one or more filters limiting the number of opportunities to present an advertisement in which advertisements from the advertising campaign are included. The scaling filters may be based on the one or more interval objectives, bid amounts determined for advertisements in the advertising campaign, and bid amounts associated with advertisements previously selected for presentation form the historical data.