Influencer Segmentation via Transaction Graph Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Predicting which individuals or entities will become influencers is challenging, as existing tools lack effectiveness in identifying potential influencers before they gain significant influence.

Innovation Solution

A method and system that utilize transaction data to generate graphs, extract feature sets, and apply machine learning models to predict influencer ranks, allowing for segmentation and targeted resource allocation based on predicted influence levels.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing tools are used to generate analytics about influencers, then some identification capability is provided, but the effectiveness in predicting potential influencers before they gain significant influence is insufficient

Engineering Contradiction:

Improveprediction effectivenessVSAvoididentification accuracy

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system performs preliminary analysis by processing transaction data before influencers gain significant influence. It extracts features from transaction graphs and generates predicted ranks in advance, allowing identification of potential influencers before they become prominent, thereby improving prediction effectiveness and identification accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary machine learning model that processes transaction data through graph representations. This intermediary layer transforms raw transaction data into predicted influencer ranks, improving the reliability and precision of influencer identification by adding a sophisticated analysis layer between data collection and identification.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If resources are allocated broadly to all entities, then coverage is maximized, but wastage occurs on less influential entities

Engineering Contradiction:

Improveresource allocation efficiencyVSAvoidresource wastage

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system segments entities into different influencer tiers based on predicted ranks generated from transaction data analysis. By dividing the population into segments with different influence levels, the system enables targeted resource allocation to high-potential influencers while reducing wastage on less influential entities, thereby improving resource allocation efficiency.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies local quality by tailoring resource allocation strategies to different entity segments based on their predicted influence characteristics. Instead of uniform treatment, entities are treated differently according to their specific predicted influencer potential, optimizing resource usage for those most likely to deliver promotional results.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12079885B2Influencer segmentation detector

Publication Date: 2024.09.03 INTUIT INC

AI summary

A method implements influencer segmentation detection. The method includes selecting transaction data for a time window and processing the transaction data for the time window to generate a graph for the time window. The method further includes extracting, from the graph, a feature set for a node of the graph for the time window and processing the feature set to generate a predicted rank for the node for a subsequent time window using a machine learning model. The method further includes selecting, using the predicted rank, an entity identifier corresponding to the node and presenting the entity identifier.