Marketing Campaign Prediction Using Augmented Customer Timelines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vendors struggle to quantify the value customers place on interactions, leading to inefficient spending on unvalued interactions and neglecting valued ones, and face challenges in attributing the impact of multiple marketing channels on purchase decisions.
Innovation Solution
A computing device analyzes customer event timelines from various data sources, augments them with marketing campaigns, and uses trained machine learning models to predict revenue and cost outcomes, enabling selection of optimal campaigns based on vendor value and customer behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If vendors spend money on multiple marketing interactions (salesperson calls, brochures, etc.), then customer reach and engagement increase, but the vendor cannot quantify the value customers place on each interaction, leading to inefficient spending
Solution Approach 1:
The system implements feedback by continuously monitoring customer interactions across multiple channels and using machine learning models to quantify the value customers place on each interaction type. This feedback loop enables vendors to adjust marketing spending based on measured customer valuation, transforming unquantified interactions into measurable, optimizable metrics that directly inform budget allocation decisions
Solution Approach 2:
The patent replaces traditional mechanical attribution methods (manual tracking, simple metrics) with an automated machine learning system that processes multi-channel interaction data. This substitution enables sophisticated quantification of customer interaction value without manual intervention, allowing vendors to efficiently measure and optimize the effectiveness of each marketing channel based on actual customer valuation
2Adaptability or versatility
If vendors expose customers to multiple messages in multiple formats via multiple media, then marketing coverage increases, but determining which particular medium primarily influenced the purchase becomes difficult
Solution Approach 1:
The system segments the complex multi-channel marketing environment into distinct, measurable interaction events across different channels (email, social media, website, mobile app). By breaking down the holistic customer journey into discrete, trackable segments, the system enables precise attribution of purchase influence to specific channels while maintaining comprehensive multi-channel coverage
Solution Approach 2:
The patent introduces a machine learning-based attribution model as an intermediary that processes data from multiple marketing channels and determines the primary influence on purchase decisions. This intermediary layer synthesizes complex multi-channel data into clear attribution insights, enabling vendors to identify which specific medium drove conversions while maintaining diverse marketing channel exposure
3Ease of operation
If vendors rely on traditional performance metrics (media impressions, website visits, clicks), then measurement simplicity is maintained, but these metrics may not directly correlate with purchase intent or customer value
Solution Approach 1:
The system transforms traditional marketing metrics by changing the underlying parameters from simple exposure counts (impressions, clicks) to value-based measurements that incorporate customer valuation of interactions. This parameter change enables precise measurement of purchase intent and customer value while maintaining operational simplicity through automated machine learning calculations that synthesize multiple data sources into actionable insights
Data Source
AI summary
In some implementations, a computing device may determine, from multiple data sources, multiple event timelines, with each event timeline associated with a customer. Each event in an event timeline represents an interaction between the customer and a vendor of goods and/or services. For N (N>1) marketing campaigns, N augmented timelines may be created for each timeline by augmenting each event timeline with the individual marketing campaigns. Thus, for M (M>1) customers, M×N augmented event timelines may be created. A trained machine learning model may perform an analysis of each augmented event timeline to predict results of executing each marketing campaign. The results may include total predicted revenue and total predicted cost resulting from executing each marketing campaign. A particular marketing campaign from the N marketing campaigns may be selected and execution of one or more marketing events may be initiated.