Machine Learning Target Identification Platform
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Organizations face challenges in effectively identifying prospective targets for campaigns due to lack of access to necessary data and inability to influence target behavior at the appropriate time, relying on categorization by business rules or market triggers.
Innovation Solution
A digital intelligence platform uses machine learning models trained on generic and contextualized features to identify prospective targets by obtaining and associating personal and activity information from various data sources, selecting optimal subsets of features, and processing requests for target lists.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are trained on multiple data sources to improve target identification accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent segments the complex target identification system into distinct functional modules: data collection module that gathers information from multiple data sources, feature extraction module that identifies relevant characteristics, machine learning model training module that develops prediction models, and target identification module that applies models to identify prospective targets. This segmentation manages complexity while maintaining high identification accuracy through specialized processing at each stage.
Solution Approach 2:
The patent introduces intermediary components including feature extraction techniques that transform raw data from multiple sources into meaningful characteristics, and profile information that serves as an intermediate representation connecting personal information with activity information. These intermediaries simplify the integration of diverse data sources while preserving the accuracy needed for precise target identification.
2Loss of information
If comprehensive personal and activity information is collected from multiple data sources, then information completeness improves, but loss of time increases
Solution Approach 1:
The patent implements preliminary action through pre-processing and feature extraction steps that prepare data from multiple sources in advance. Profile information is generated beforehand by associating personal information with activity information, and feature identification techniques pre-analyze data to extract relevant characteristics. This preliminary processing ensures information completeness is achieved without excessive delays when actual target identification is needed.
3Manufacturing precision
If feature identification techniques are used to determine optimal feature subsets, then manufacturing precision improves, but device complexity increases
Solution Approach 1:
The patent applies local quality by using different feature identification techniques for different types of features and different data sources. Generic features may use one identification approach while contextualized features associated with specific individual segments use another approach. This localized application of feature selection methods optimizes model training precision for each feature type while managing overall system complexity through targeted rather than universal processing.
Data Source
AI summary
A device may obtain, from a collection of data sources, personal information and activity information for a group of individuals. The device may generate profile information by associating the personal information and the activity information for each individual in the group of individuals. The device may determine a set of features capable of being used to train a set of machine learning models by using one or more feature identification techniques to analyze the profile information. The set of features may include generic features and contextualized features associated with the group of individuals. The device may train the set of machine learning models using one or more subsets of features of the set of features. The device may use the set of machine learning models to process a request from a client device for a list of prospective targets for a campaign.