Machine-Learning Visitor Lifetime Value for Vehicle Dealer SEM

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing search engine marketing (SEM) systems fail to accurately predict the likelihood of a user making a purchase from a dealer, leading to inefficient targeting of online advertisements, as they assume uniform conversion rates among all users, disregarding individual browsing behaviors and dealer characteristics.

Innovation Solution

A vehicle data system (VDS) utilizes machine learning to analyze user interactions, dealer features, and vehicle-related data to determine a user's lifetime value, which is then communicated to search engines to improve SEM processes by prioritizing users likely to convert.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If search engine marketing systems use uniform conversion rates for all users, then the system is simple to operate, but the accuracy of predicting purchase likelihood deteriorates

Engineering Contradiction:

Improvesystem operation simplicityVSAvoidpurchase likelihood prediction accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system segments users into different categories based on their browsing behaviors, dealer interactions, and conversion probabilities. Instead of treating all users uniformly, the system divides the user base into segments with different conversion characteristics, allowing for more accurate prediction while maintaining operational simplicity through automated segmentation algorithms.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes the conversion rate parameter from a fixed uniform value to a dynamic parameter that varies based on user behavior patterns, dealer characteristics, and interaction history. This allows the system to adapt conversion rate estimates to individual users and situations, improving prediction accuracy without requiring manual configuration.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If the system analyzes individual user behaviors and dealer characteristics to determine lifetime value, then the prediction accuracy improves, but the device complexity increases

Engineering Contradiction:

Improvelifetime value determination accuracyVSAvoidsystem structural complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically collecting, processing, and analyzing user behavior data and dealer characteristics without requiring manual intervention. The machine learning models autonomously learn from historical data and update their predictions, reducing the need for complex manual analysis while maintaining high accuracy in lifetime value determination.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces manual analysis mechanisms with automated machine learning algorithms that process large volumes of data efficiently. Instead of requiring complex manual evaluation procedures, the system uses computational models that automatically identify patterns and predict lifetime values, reducing operational complexity while improving accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If the system targets users with higher conversion probabilities, then the sales likelihood increases, but the loss of information about other users increases

Engineering Contradiction:

Improvesales conversion rateVSAvoiduser data utilization

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The system applies local quality by tailoring marketing strategies to specific user segments and dealer characteristics rather than applying a one-size-fits-all approach. By analyzing local patterns in user behavior and dealer performance, the system identifies high-conversion opportunities while still maintaining an overall understanding of the broader user population, preventing information loss.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system performs preliminary analysis of user behaviors and dealer characteristics to pre-identify high-conversion probability users before marketing campaigns are executed. This preliminary segmentation allows the system to focus resources on likely converters while maintaining records and analysis of other users for future reference, preventing information loss through proactive data management.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250217826A1Systems and methods for determining lifetime value of website visitor through machine learning

Publication Date: 2025.07.03 TRUECAR INC

AI summary

A vehicle data system receives a lead submission through a website supported by the vehicle data system and determines, utilizing a machine learning model, a user value for a lead associated with the lead submission. The user value represents a probability of the lead purchasing a vehicle from a dealer through the website. The vehicle data system determines a user lifetime value for the lead based at least on the user value for the lead. Subsequently, the vehicle data system obtains clickstream identifiers from a search engine and assigns a corresponding user lifetime value to each clickstream identifier. The vehicle data system aggregates the clickstream identifiers and corresponding user lifetime values in a single file and communicates the single file to a search server for consumption. The user lifetime values are utilized by the search engine in search engine marketing processes.