Ad Impression Value Prediction via Brain Engine
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for determining market values of ad impressions lack accuracy and efficiency, particularly in predicting competitive market values and managing bid aggressiveness, leading to suboptimal advertising campaigns.
Innovation Solution
A method and system where a brain engine within a demand side platform (DSP) predicts competitive market values for ad impressions by analyzing candidate inputs, including campaign goals, budget, and past bid data, and adjusts bid aggressiveness based on a scaling factor to optimize ad campaign performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional bidding systems are used to determine market values of ad impressions, then the system complexity is low and ease of operation is maintained, but the measurement precision of market values is insufficient and bidding accuracy deteriorates
Solution Approach 1:
The patent introduces a brain engine as an intermediary component between the DSP and ad exchanges. This brain engine specializes in predicting competitive market values by analyzing candidate inputs and bid data, thereby improving measurement precision without requiring the entire bidding system to become overly complex. The brain engine acts as a dedicated prediction module that handles the analytical complexity internally while presenting simplified bid recommendations to the user.
Solution Approach 2:
The patent segments the bidding system into distinct functional modules: a brain engine for prediction, a DSP for bid management, and integration with ad exchanges. By dividing the system into specialized components, each module can focus on specific tasks (prediction, bid adjustment, execution) which improves overall measurement precision while managing complexity through modular architecture.
2Reliability
If competitive market value prediction is implemented to improve bidding accuracy, then the reliability of ad campaign performance is improved, but the loss of time for data analysis and processing increases
Solution Approach 1:
The brain engine performs preliminary actions by pre-analyzing candidate inputs, historical bid data, and market conditions to generate competitive market value predictions before actual bidding occurs. This advance prediction allows the DSP to make informed bid decisions without time-consuming analysis during the bidding moment, thereby improving reliability while minimizing time loss during critical bidding windows.
Solution Approach 2:
The system implements self-service through automated data collection, analysis, and bid recommendation generation. The brain engine automatically processes candidate inputs and historical data without requiring manual intervention, and the DSP automatically adjusts bid aggressiveness based on predictions. This automation reduces time loss by eliminating manual analysis steps while maintaining high reliability through consistent algorithmic processing.
3Productivity
If bid aggressiveness adjustment based on scaling factors is used to optimize campaign ROI, then the productivity of ad spending is improved, but the difficulty of detecting and measuring optimal bid levels increases
Solution Approach 1:
The patent applies parameter changes by introducing a bid aggressiveness scaling factor that dynamically adjusts bid amounts based on predicted competitive market values. Instead of using fixed bid strategies, the system modifies the bid parameter (aggressiveness level) according to real-time predictions and campaign performance, thereby improving productivity by optimizing spend while using a measurable parameter (scaling factor) to control the adjustment.
Solution Approach 2:
The system implements feedback loops where bid results and campaign performance data are continuously fed back to the brain engine and DSP. This feedback enables the system to learn from past bidding outcomes and adjust future bid aggressiveness levels accordingly. The feedback mechanism makes optimal bid levels detectable and measurable by tracking performance metrics against predictions, allowing the system to refine its scaling factors based on actual results.
Data Source
AI summary
The present disclosure is directed to methods and systems for determining competitive market values for an ad impression on an advertiser exchange. An engine executing on a device may receive a candidate set of inputs associated with ad impressions. The engine may determine competitive market values for an ad impression on an advertiser exchange. The engine may determine candidate clearing prices based on the candidate set of inputs and history of clearing prices on the advertiser exchange. The engine may generate, based on the candidate clearing prices, a competitive market value prediction for the ad impression on the advertiser exchange. The competitive market value prediction may comprise a distribution function of predicted clearing prices on the advertiser exchange. The engine may generate, based on the competitive market value prediction, a fair market value bid for the ad impression in the context of a specific ad campaign.