Campaign Item Modification with Dual-Stage ML Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual adjustment of marketing campaign items is time-consuming and relies heavily on human operator experience, leading to inefficiencies and variable results.
Innovation Solution
Implement a system using two machine learning algorithms (MLAs) to predict and recommend changes to campaign items, including a categorical MLA for action type and a continuous MLA for change magnitude, with user input for adjustment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual adjustment of campaign items is performed by human operators, then the adjustments can be made based on experience and skill, but the process is time-consuming and results are variable
Solution Approach 1:
The patent replaces the manual mechanical process of human operators reviewing and adjusting campaign items with automated machine learning algorithms. The MLA processes campaign data, performance metrics, and historical information to generate predictions and recommendations, eliminating the time-consuming manual review process while maintaining or improving adjustment quality through consistent application of learned patterns
Solution Approach 2:
The system enables campaign optimization to occur automatically without requiring continuous human intervention. The MLA continuously processes campaign data and generates adjustments based on learned patterns from historical performance, allowing the system to self-optimize campaigns while human operators only need to review and approve recommendations, significantly reducing the time investment required
2Productivity
If manual adjustment processes are used, then human operators can apply their experience, but the process becomes complex and difficult to standardize
Solution Approach 1:
The patent segments the complex campaign optimization process into distinct functional components handled by the MLA: data collection and processing, performance metric analysis, prediction generation, recommendation formulation, and adjustment implementation. This segmentation transforms the unwieldy manual process into manageable, standardized automated steps that can be executed consistently
Solution Approach 2:
The system standardizes the optimization process by transforming qualitative human judgment into quantitative parameters that the MLA can process. Campaign performance, historical data, and adjustment criteria are converted into numerical parameters and structured data formats, enabling consistent automated decision-making while improving productivity through efficient data processing
3Reliability
If frequent reviews and adjustments are made to campaign items, then campaign performance can be optimized, but the manual process becomes increasingly time-consuming
Solution Approach 1:
The patent enables continuous campaign optimization by having the MLA operate automatically without interruption. The system continuously collects campaign data, processes performance metrics, generates predictions, and implements adjustments in an unbroken cycle, ensuring optimal performance at all times without the gaps and delays inherent in manual periodic reviews
Solution Approach 2:
The MLA performs preliminary analysis and prediction before actual campaign adjustments are needed. By continuously processing data and generating recommendations in advance, the system is ready to implement optimizations immediately when conditions change, reducing the duration from problem identification to solution implementation while maintaining reliable performance optimization
Data Source
AI summary
There is disclosed a method and system for modifying campaign items. Data corresponding to a campaign item may be retrieved. The data may be input to a first machine learning algorithm (MLA) trained to predict a type of change to a campaign item. A first prediction that indicates a type of change to for the campaign item may be received from the first MLA. The data corresponding to the campaign item and the first prediction may be input to a second MLA that was trained to predict a magnitude of the type of change to the campaign item. The second MLA may output a second prediction that indicates a magnitude corresponding to the first prediction. A user interface may be output that includes the first prediction and the second prediction as a recommendation.