Aggregated Device Data for Future Viewership Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Content providers face challenges in accurately predicting viewership fluctuations for targeted advertising, leading to inconsistent campaign results due to limited device resources and restricted access to data, resulting in inefficient deployment strategies.
Innovation Solution
A system and method for predicting viewership probability using a computer-implemented approach that aggregates data from multiple devices, employs Automatic Content Recognition (ACR) to identify content, and utilizes machine learning models to generate predictive metrics, comparing them against a baseline for performance tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If content providers use broad approach in deploying advertising campaigns, then advertising reach is maximized, but campaign results become inconsistent due to viewership fluctuations
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing viewership data before advertising campaigns are deployed. Machine learning models are trained in advance on historical viewership patterns to predict future viewership probabilities, enabling content providers to make informed deployment decisions ahead of time. This preliminary analysis allows optimization of campaign timing and targeting to achieve consistent results.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring actual viewership outcomes and comparing them with predicted probabilities. This feedback loop allows the machine learning models to be retrained and refined over time, improving prediction accuracy and enabling continuous optimization of advertising campaign deployment strategies for consistent performance.
2Productivity
If content providers deploy advertising campaigns without accurate viewership prediction, then deployment speed is maintained, but resource allocation becomes inefficient
Solution Approach 1:
The system performs preliminary viewer identification and probability scoring before campaign deployment. By pre-calculating which devices are likely to view content and assigning probability scores, the system enables rapid targeted deployment without requiring extensive resource allocation during the actual campaign execution, thus maintaining deployment speed while improving resource efficiency.
3Device complexity
If device resources are limited for data collection and processing, then device complexity is reduced, but viewership prediction accuracy deteriorates
Solution Approach 1:
The system introduces intermediary components including centralized data aggregation servers and machine learning model processing systems. These intermediaries handle the complex tasks of data collection, merging, and predictive modeling, allowing individual devices to remain simple while the overall system achieves high prediction accuracy through distributed intelligence and centralized processing.
Solution Approach 2:
The system merges data from multiple partnering devices to create comprehensive training datasets. By combining viewership data across many devices, the system overcomes the limitations of individual device resources and creates sufficiently large and diverse datasets for training accurate machine learning models, thereby achieving high prediction accuracy without requiring complex individual devices.
4Measurement precision
If data from multiple partnering devices is merged and aggregated, then prediction accuracy is improved, but data processing complexity increases
Solution Approach 1:
The system segments the data processing workflow into distinct stages: data collection at individual devices, data merging at intermediary servers, aggregation into training datasets, and model training/separation. This segmentation allows each component to handle specific tasks efficiently, managing overall data processing complexity while achieving high prediction accuracy through systematic multi-stage processing.
Data Source
AI summary
Approaches provide for predictive viewership associated with a device. Information associated with viewership by the device may be received over an interval. The received viewership information is merged with panel information to further generate merged information. The merged information is then aggregated at a predetermined increment to form aggregated date. The aggregated data can then be used as input training data to a model to generate probability of viewership by the device. One or more metrics associated with the predicted viewership can be tracked to evaluate model performance.