Neural Network Propensity Scoring for Marketing Targeting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for targeting marketing efforts to prospective customers are inefficient due to reliance on generalized assumptions and the vast amount of data, leading to improper identification of customer interests and increased waste from irrelevant communications.

Innovation Solution

A system utilizing a machine learning program with a neural network to predict customer propensity for purchasing products or services based on personal data, sending targeted communications when a predicted probability meets a threshold.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If generalized assumptions are used to target marketing to prospective customers, then the marketing process is simple and quick, but the accuracy of identifying customer interest is poor leading to improper identification

Engineering Contradiction:

Improveaccuracy of identifying customer interestVSAvoidcomplexity of marketing targeting system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical/statistical marketing targeting systems with an AI-based neural network system. The neural network automatically processes customer data, interaction history, and behavioral patterns to generate propensity scores, substituting manual segmentation and rule-based targeting with intelligent automated decision-making that improves accuracy without requiring manual complexity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an AI propensity scoring system as an intermediary between raw customer data and marketing decisions. This intermediary layer processes and interprets complex interaction data, transforming it into actionable propensity scores that guide targeted marketing, thereby resolving the contradiction between data complexity and decision accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If the vast amount of available customer data is analyzed using traditional methods, then comprehensive customer insights could be obtained, but the difficulty of finding relevant relationships within the data increases

Engineering Contradiction:

Improvecompleteness of customer insightsVSAvoiddifficulty of finding relevant relationships in data

Core Design Contradiction:

Loss of informationVSDifficulty of detecting and measuring

Solution Approach 1:

The patent replaces traditional data analysis methods with neural network-based AI processing. The neural network automatically detects complex patterns and relationships in vast customer data sets, interaction logs, and behavioral information, transforming the manual process of finding relevant relationships into an automated intelligent process that handles data complexity efficiently

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses neural networks that learn from training data by creating internal representations (copies) of customer behavior patterns. The network learns from historical interaction data and creates probabilistic models that can predict future behavior, effectively copying and generalizing from past patterns without requiring manual analysis of each data relationship

Inventive Principle:

Principle #26Copying

3Loss of energy

If marketing communications are sent to all prospective customers, then no customer is missed, but waste from irrelevant communications increases and customer engagement decreases

Engineering Contradiction:

Improvewaste from irrelevant communicationsVSAvoidreliability of customer engagement

Core Design Contradiction:

Loss of energyVSReliability

Solution Approach 1:

The patent applies local quality by segmenting the customer base into distinct groups based on AI-calculated propensity scores. Instead of uniform marketing to all customers, the system tailors communication intensity and targeting to local customer characteristics, sending marketing materials only to those in specific propensity ranges who are most likely to engage, thereby reducing waste while maintaining engagement reliability

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent implements partial action by sending marketing communications only to a subset of customers who meet predetermined propensity thresholds. Rather than excessive action (sending to all customers), the system applies partial targeting to those most likely to respond, reducing communication waste while maintaining sufficient market coverage through intelligent selection

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20230342597A1Using machine learning to extract subsets of interaction data for triggering development actions

Publication Date: 2023.10.26 TRUIST BANK

AI summary

A system for guiding interactions with a user device includes a computer generating a predictive model during training of a machine learning program utilizing at least one neural network. A training data set utilized during the training of the machine learning program includes a personal data set of each of a plurality of first users. The predictive model predicts a probability of a second user associated with the user device interacting with a first product and/or service. The predicting of the probability including the predictive model correlating a personal data set of the second user to the personal data set of at least one first user. The computer sends a communication to the user device of the second user including content relating to the first product and/or service when the predicted probability meets or exceeds a threshold value.