Streaming Session Crediting via ML Cluster Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for crediting streaming sessions often inaccurately associate media with streaming sources due to incorrect device-to-TV associations or other errors, leading to illogical associations and incorrect data usage by audience measurement entities.
Innovation Solution
A system utilizing machine learning circuitry and a cluster landscape model, implemented with DBSCAN algorithm, to validate and correct media/streaming source associations by analyzing session information and identifying valid streaming sessions, preventing invalid associations from being credited.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to credit streaming sessions, then the crediting process is simple and fast, but the accuracy of media-streaming source associations deteriorates due to incorrect device-to-TV associations
Solution Approach 1:
The patent introduces machine learning circuitry as an intermediary component between the meter and the credit database. This intermediary validates media-streaming source associations by analyzing multiple parameters (device identifiers, TV identifiers, session information) and determining whether associations are logical and accurate before crediting, thereby improving measurement precision without requiring fundamental changes to the existing crediting infrastructure
Solution Approach 2:
The system implements feedback mechanisms where the machine learning model continuously learns from validated associations and adjusts its validation criteria. The model receives feedback about association accuracy and refines its ability to distinguish valid from invalid associations, improving measurement precision over time while maintaining manageable system complexity through iterative improvement
2Reliability
If machine learning validation is implemented to improve association accuracy, then the reliability of crediting improves, but the device complexity and computational requirements increase
Solution Approach 1:
The machine learning validation system applies partial validation by focusing on the most critical association parameters rather than validating every possible aspect of each streaming session. This selective validation approach maintains high reliability for the most important associations while keeping computational complexity and device requirements manageable by not over-validating
Data Source
AI summary
Methods, apparatus, systems, and articles of manufacture to accurately credit streaming sessions are disclosed. A meter device records streaming session information. Cluster creation circuitry trains a model by grouping information from multiple streaming sessions into clusters, wherein all streaming sessions within a given cluster have matching media and streaming sources. Model executor circuitry assigns incoming streaming session information to a cluster or to noise. Cluster creation circuitry edits the model by creating new clusters out of information from multiple streaming sessions with similar attributes that were originally labeled as noise. By only crediting streaming session information assigned to a cluster, the disclosed system avoids crediting illogical streaming session information, such as the crediting of media to a streaming source that does not offer said media.