Touchpoint Attribution Attention Neural Network for Campaign Reach

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional digital content dissemination systems are inaccurate, inefficient, and inflexible in attributing touchpoints and predicting user interactions, leading to unnecessary resource expenditure and ineffective digital content campaigns.

Innovation Solution

A deep learning attribution system employing a touchpoint attribution attention neural network that includes an attention layer, a time-decay parameter, and a user bias control model to accurately identify significant touchpoints and measure their influence in digital content campaigns, flexibly modeling interactions between media channels, user characteristics, and temporal effects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional digital content dissemination systems provide customized digital content through multiple digital media channels, then the reach and coverage of digital content campaigns is improved, but the accuracy in identifying which touchpoints result in user actions deteriorates

Engineering Contradiction:

Improvedigital content campaign reachVSAvoidtouchpoint attribution accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system dynamically adjusts attribution weights based on observed user behavior patterns and contextual factors rather than using fixed rules. The neural network continuously learns from new data to refine touchpoint contribution estimates, making the attribution model adaptive to changing user interactions across multiple media channels.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameters of attribution by incorporating multiple factors including time decay, user characteristics, and contextual variables into the neural network model. This allows the system to evaluate touchpoint contribution with varying weights based on specific conditions rather than uniform attribution rules.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If conventional digital content dissemination systems continue to expend computing resources to achieve desired campaign results, then the target reach is improved, but the efficiency and resource utilization deteriorates

Engineering Contradiction:

Improvecampaign target reachVSAvoidcomputing resource consumption

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system performs partial attribution analysis by focusing computational resources on identifying the most significant touchpoints rather than exhaustively analyzing every possible touchpoint. The neural network learns to prioritize key attribution factors, reducing unnecessary computations while maintaining accurate campaign performance measurement.

Inventive Principle:

Principle #16Partial or excessive action

3Device complexity

If conventional digital content dissemination systems utilize rigid pre-determined rules for touchpoint attribution, then the system complexity is reduced, but the adaptability to fluid user interactions and complex media channel interactions deteriorates

Engineering Contradiction:

Improveattribution system complexityVSAvoidflexibility in modeling user interactions

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The system replaces mechanical rule-based attribution methods with a neural network-based intelligent system. This substitution enables the system to automatically learn complex patterns in user behavior and media channel interactions without requiring explicit programming of attribution rules, thereby increasing adaptability while managing complexity through automated learning.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11816272B2Identifying touchpoint contribution utilizing a touchpoint attribution attention neural network

Publication Date: 2023.11.14 ADOBE INC

AI summary

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating and utilizing a touchpoint attribution attention neural network to identify and measure performance of touchpoints in digital content campaigns. For example, a deep learning attribution system trains a touchpoint attribution attention neural network using touchpoint sequences, which include user interactions with content via one or more digital media channels. In one or more embodiments, the deep learning attribution system utilizes the trained touchpoint attribution attention neural network to determine touchpoint attributions of touchpoints in a target touchpoint sequence. In addition, the deep learning attribution system can utilize the trained touchpoint attribution attention neural network to generate conversion predictions for target touchpoint sequences and to provide targeted digital content over specific digital media channels to client devices of individual users.