PID Controller Engine for Real-Time Online Campaign Pacing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing online advertising systems face challenges in controlling the pace of campaigns to ensure timely and efficient budget spending while reaching the desired targeted audience, often resulting in campaigns either expending their budget too quickly or extending beyond the allotted runtime, due to unpredictable opportunities for ad placement.
Innovation Solution
The implementation of a PID Controller Engine that uses real-time data and machine learning models to adjust bidding strategies based on targeting parameters, ensuring a desired distribution of ad placements and budget expenditure over the campaign runtime, optimizing for cost efficiency and audience reach.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional online advertising systems place ads based on random opportunities without pace control, then ad placements can be made quickly, but the budget is spent too early or the campaign extends beyond allotted runtime
Solution Approach 1:
The system dynamically adjusts bidding strategies and ad placement pacing based on real-time campaign performance data. The pace control mechanism continuously monitors budget consumption and remaining runtime, adapting the aggressiveness of bid submissions to maintain optimal spending rates throughout the campaign lifecycle, thereby resolving the contradiction between placement speed and runtime control.
Solution Approach 2:
The system implements feedback loops that monitor actual campaign performance against planned pacing targets. By continuously measuring budget spend rates and comparing them to ideal trajectories, the system adjusts future bidding behavior to correct deviations, ensuring the campaign stays within allotted runtime while maintaining productive ad placement rates.
2Loss of time
If the system chooses poor viewer targets towards the end of the campaign to prevent extension, then campaign runtime is controlled, but advertising efficiency and budget productivity decrease
Solution Approach 1:
The system dynamically optimizes viewer targeting throughout the campaign based on real-time performance data and remaining runtime. Rather than static targeting rules, the system adapts its viewer selection criteria as the campaign progresses, intensifying efforts to reach remaining budget goals in the final stages while maintaining efficiency through data-driven audience selection rather than arbitrary poor targets.
Solution Approach 2:
The system changes targeting parameters and bidding aggressiveness as functions of campaign progress and remaining budget. By adjusting viewer target quality thresholds and bid amounts based on real-time pace analysis, the system maintains advertising efficiency throughout the campaign, including the final stages, rather than resorting to poor viewer targets.
3Quantity of substance
If the system chooses more expensive targets to fill remaining budget, then budget is spent completely, but cost efficiency and return on advertising investment decrease
Solution Approach 1:
The system performs preliminary pacing analysis and budget allocation planning at the start of the campaign, establishing ideal spending trajectories. By proactively managing budget consumption throughout the campaign based on pre-calculated pacing models, the system ensures complete budget utilization without resorting to expensive last-minute targets, as the pacing strategy is already optimized to spend the full budget efficiently by the campaign end.
Solution Approach 2:
The system continuously monitors actual spending against planned budget trajectories and adjusts bidding strategies in real-time. This feedback mechanism allows the system to accelerate or decelerate spending as needed to achieve complete budget utilization while maintaining cost efficiency, preventing the need to purchase expensive impressions in the final stages.
Data Source
AI summary
The invention uses a PID controller engine to provide a desired distribution of targeted ad placements, including controlling campaign pace in realtime to precisely spend a campaign budget over a prescribed runtime, while producing optimum results in a cost efficient manner based on desired targeting parameters. Those parameters include one or more probabilities that a viewer associated with an ad impression opportunity: belongs to one or more targeted demographic categories; will convert with respect to a product or service being offered; has an intention to buy the product or service; or exhibits one or more defined behaviors. Probabilities are determined by a truth-based machine-learning modelling engine. Upon receiving an ad slot opportunity package, a DSP makes a bid decision and determines a bid price, and then sends a bid response to the supply-side partner, all within 200 mS of receiving the ad slot opportunity or the bid will be ignored.