Frequency Histogram Modeling for Digital Transmission Reach Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack effective methods to accurately predict the reach and frequency of digital component transmissions to user devices, leading to inefficiencies in resource allocation and potential over or under-exposure of digital content.
Innovation Solution
A reach and frequency planning system that uses a frequency model trained on observed transmission commitments to generate predictions for hypothetical scenarios, utilizing parametric probability distributions and numerical optimization techniques to optimize predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If direct measurement of reach and frequency is performed for each transmission commitment, then measurement accuracy is improved, but resource consumption and time requirements increase significantly
Solution Approach 1:
The system performs preliminary actions by collecting transmission commitment data and user exposure data in advance, then trains a machine learning model offline to establish predictive relationships. This allows the model to be ready for rapid prediction without requiring time-consuming direct measurements when actual reach and frequency predictions are needed.
Solution Approach 2:
Instead of performing direct measurements for each new transmission commitment, the system creates a predictive copy through a trained machine learning model that replicates the measurement function. The model learns from historical data and can generate predictions that approximate direct measurements without actually performing the full measurement process again.
2Measurement precision
If direct measurement of reach and frequency is performed for each transmission commitment, then measurement accuracy is improved, but resource consumption increases
Solution Approach 1:
The system performs computationally intensive model training in advance when resources are available, then uses the trained model for efficient predictions. This shifts the resource consumption to a preliminary phase, allowing rapid low-cost predictions when actual resource constraints are tighter.
Solution Approach 2:
The trained machine learning model serves as a computational copy that can generate predictions with fraction of the resource cost of direct measurements. Once the model is trained, it can be deployed and reused multiple times without repeating the full measurement and computation process.
3Quantity of substance
If transmission commitments are increased to improve reach, then user coverage is improved, but user exposure frequency becomes uncontrolled leading to overexposure
Solution Approach 1:
The system uses predictive feedback to estimate both reach and frequency outcomes before actually implementing transmission commitments. By feeding the predicted frequency histogram back to planners, the system enables adjustment of transmission strategies to achieve desired reach while maintaining frequency within acceptable ranges, preventing overexposure.
Solution Approach 2:
The system changes the approach from direct control of transmission numbers to control through predicted outcome parameters. By using the frequency histogram and predictive model, planners can adjust transmission commitments based on predicted reach and frequency outcomes rather than simply controlling transmission volume, enabling better balance between reach and frequency.
4Ease of operation
If transmission commitments are reduced to control frequency, then user overexposure is prevented, but reach becomes insufficient
Solution Approach 1:
The predictive model provides feedback on both frequency and reach outcomes simultaneously, allowing planners to see the trade-offs before committing to transmission levels. This enables optimization of transmission commitments to achieve adequate reach while maintaining frequency control, rather than having to choose one objective at the expense of the other.
Solution Approach 2:
The system enables control through predicted outcome parameters rather than direct transmission control. By adjusting transmission commitments based on predicted reach and frequency from the frequency histogram, planners can achieve better balance between these two objectives compared to controlling only one parameter directly.
Data Source
AI summary
In one aspect, there is provided a method performed by one or more computers that includes: obtaining an observed frequency histogram corresponding to an observed transmission commitment, where a transmission commitment specifies a number of transmissions of a digital component; generating a frequency model based on the observed frequency histogram, where the frequency model is a parametric model parameterized by a set of model parameters; receiving a request to predict a frequency histogram corresponding to a target transmission commitment; processing data defining the target transmission commitment using the frequency model to generate a predicted frequency histogram corresponding to the target transmission commitment; and generating one or more predictions characterizing the target transmission commitment using the predicted frequency histogram.