Interactive Cross-Channel Predictive Model Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Legacy advertising portfolio management techniques fail to accurately measure the effectiveness of advertising campaigns across multiple channels, as they rely on naive one-to-one correspondences between ad placements and responses, neglecting cross-channel influences and not accounting for recent changes in media spending, leading to inadequate responsiveness and interactivity.
Innovation Solution
A method for performing interactive updates to a precalculated cross-channel predictive model, which receives data on marketing stimuli and responses, forms a multi-channel simulation model to determine cross-channel weights, and updates the model to reflect new marketing stimuli, allowing for the calculation of effectiveness values based on these weights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a precalculated cross-channel predictive model is used, then measurement precision of advertising effectiveness is improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent pre-calculates cross-channel weights using historical data and stores them in a predictive model before actual advertising campaigns. This preliminary computation of channel interaction weights avoids complex real-time calculations during campaign execution, resolving the contradiction between measurement precision and computational complexity.
Solution Approach 2:
The patent creates a simplified predictive model that copies and stores pre-computed cross-channel weights from historical analysis. Instead of performing complex cross-channel effect calculations for each advertising decision, the system uses this copied predictive model with pre-determined weights, reducing computational complexity while maintaining measurement precision.
2Adaptability or versatility
If cross-channel weights are recalculated in real-time, then adaptability to changing media spending is improved, but loss of time and computational resources increase
Solution Approach 1:
The patent implements a feedback mechanism where the predictive model is periodically updated with new historical data and recalibrated. This allows the model to adapt to changing media spending patterns and cross-channel effects over time without requiring continuous real-time recalculation, balancing adaptability with time efficiency.
Solution Approach 2:
The system performs preliminary updates of cross-channel weights at scheduled intervals using accumulated historical data, rather than recalculating in real-time for each spending change. This preliminary batch processing approach maintains adaptability to trends while avoiding the time loss of continuous real-time computation.
3Measurement precision
If detailed cross-channel analysis is performed, then measurement precision is improved, but device complexity and data processing requirements increase
Solution Approach 1:
The patent extracts and isolates the critical cross-channel interaction weights from complex multi-channel advertising data. By separating these key weights into a dedicated predictive model, the system achieves precise measurement of channel effectiveness without requiring the full complexity of the original multi-channel analysis system to be active during campaign execution.
Solution Approach 2:
The system creates a simplified copy of the cross-channel relationships in the form of a predictive model with pre-determined weights. This copied model captures the essential cross-channel effects without requiring the complex data processing infrastructure needed for detailed real-time analysis, reducing system complexity while maintaining measurement precision.
Data Source
AI summary
A computer-implemented method, simulation and prediction system, and computer program product for advertising portfolio management. Embodiments commence upon receiving data comprising a plurality of marketing stimulations and respective measured responses, both pertaining to a first time period. A computer is used to form a multi-channel simulation model, where the simulation model accepts the marketing stimulations then outputs simulated responses. The simulation model is used for determining cross-channel weights to apply to the respective measured responses pertaining to the first time period. The simulation model is updated to reflect updated marketing stimulations pertaining to a second time period. The updated marketing stimulations overwrite some of the plurality of marketing stimulations captured in the first time period. The updated simulation model is used in calculating an effectiveness value of a particular one of the updated marketing stimulations based at least in part on the cross-channel weights determined for the first time period.