Audience Classification via Geolocation History Impurity Measures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing geolocation analytics systems lack specificity in identifying homogenous populations based on user behavior, often relying on poorly correlated current location data and disregarding meaningful information in high-dimensional user data.
Innovation Solution
A process of learning an audience member function by obtaining a training set of geographic data, retrieving attributes from a geographic information system, calculating impurity measures for candidate feature functions, and selecting features based on these measures to improve audience classification and content targeting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current geographic location data is used for audience classification, then the system can provide location-based analytics, but the classification accuracy deteriorates due to poor correlation between current location and user behavior
Solution Approach 1:
The patent transitions from using single-dimension current location data to multi-dimensional location history data. By incorporating temporal and spatial patterns across multiple visited locations, the system creates a more robust profile that better correlates with user behavior, thereby improving classification accuracy while maintaining reliability.
Solution Approach 2:
The system performs preliminary analysis of location histories to identify behavioral patterns before making audience classification decisions. By pre-processing location data to extract meaningful patterns and characteristics, the system prepares more accurate input for classification algorithms, improving both accuracy and reliability.
2Measurement precision
If high-dimensional user data is collected to improve audience description precision, then comprehensive behavioral insights are captured, but the system complexity increases making data processing difficult
Solution Approach 1:
The patent extracts only the most relevant features and patterns from high-dimensional location data rather than processing all raw data. By identifying and extracting key behavioral indicators from location histories, the system achieves precise audience description while reducing processing complexity through selective feature extraction.
Solution Approach 2:
The system transforms raw high-dimensional location data into simplified behavioral parameters and patterns. By changing the representation from raw coordinates and timestamps to meaningful behavioral parameters, the system maintains description precision while reducing the complexity of data processing and analysis.
Data Source
AI summary
Provided is a process of learning an audience member function, the process including: obtaining a training set of geographic data describing geolocation histories of a plurality of mobile devices, wherein members of the training set are classified according to whether the respective member of the training set is a member of an audience; retrieving attributes of geolocations in the geolocation histories from a geographic information system; learning feature functions of an audience member function based on the training set, wherein at least some of the feature functions are a function of the retrieved attributes of geolocation, wherein the feature functions are learned, at least in part, by calculating a plurality of impurity measures for candidate feature functions and selecting one of the candidate feature functions based on the relative values of the impurity measures; and storing the feature functions of the audience member function in an audience repository.