Multi-source Data Analytics System Adjusting for Promotional Bias
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data analytics systems for digital media platforms face challenges in accurately measuring the performance of digital content items across multiple sources, as they often rely on traditional metrics like page views and time spent, which do not account for promotional biases and user engagement effectively, leading to incomplete assessments of content value.
Innovation Solution
A data manager system that calculates performance indicators such as user performance indicators, subscriber performance indicators, and overall performance indicators by analyzing traffic data, promotion data, and user interactions, adjusting for promotional biases and user types, to provide a comprehensive evaluation of digital content items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional metrics like page views and time spent are used to measure content performance, then the measurement is simple and easy to implement, but the measurement precision is insufficient as it does not account for promotional biases and user engagement effectively
Solution Approach 1:
The patent segments content performance measurement into multiple independent components: base performance metrics (page views, time spent), promotional bias metrics (promotion impressions, promotion duration), and user engagement metrics (interaction types, engagement score). Each component is calculated separately and then integrated to form the overall adjusted performance metric, allowing for precise measurement while maintaining systematic organization
Solution Approach 2:
The patent introduces an intermediary adjustment mechanism that acts as a mediator between raw performance data and final performance assessment. The adjustment factor, calculated based on promotional bias and user engagement, serves as an intermediary variable that modifies the base metrics to produce the adjusted performance metric, thereby eliminating promotional distortion without requiring complete system redesign
2Measurement precision
If adjusted performance metrics accounting for promotional bias are calculated, then the measurement precision improves, but the calculation complexity and processing time increase
Solution Approach 1:
The patent performs preliminary actions by pre-calculating and storing base performance metrics (page views, time spent) and promotional metrics (promotion impressions, duration) in separate data structures before the adjustment calculation. This preliminary organization of data allows the final adjusted performance metric to be computed quickly by simply combining the pre-processed components, reducing the time penalty of increased precision
3Adaptability or versatility
If comprehensive data from multiple sources is analyzed, then the assessment completeness improves, but the device complexity and data processing requirements increase
Solution Approach 1:
The patent implements a universal data processing framework that handles multiple data sources (content management system, promotion management system, user interaction system) through a single integrated architecture. The data manager uses standardized processing routines that can accommodate different data types and sources, making the system versatile and adaptable without requiring separate complex processing paths for each data source
Solution Approach 2:
The patent merges data from multiple independent sources (content performance data, promotion data, user interaction data) into a unified adjusted performance metric. By combining these disparate data streams through a standardized adjustment formula, the system achieves comprehensive assessment while avoiding the complexity of maintaining separate analysis systems for each data source
Data Source
AI summary
The present disclosure provides a multi-source data analytics system, data manager, and related methods. The multi-source data analytics are measured and used to generate an overall performance indicator. In some examples, the overall performance indicator relates to digital content items available on a digital media platform. The digital media platform obtains relevant data from multiple sources (or channels) and calculates the overall performance indicator so as to account for one or a combination of promotional bias of at least some data sources, user visits (or interactions/views), user engagement, user recirculation, or user acquisition and retention (e.g., subscriber acquisition and retention) for one or more of the multiple data sources. The overall performance indicator may be used by a data manager to locate content on the digital media platform for more effective interaction among other uses.