Customer Purchase Prediction Score Using Payment Difference and Behavior Factors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing CRM software in the automotive industry relies on unsophisticated data mining methods that fail to accurately predict customer purchasing behavior, as they primarily focus on financial data and do not consider other influential factors in the decision-making process.
Innovation Solution
A method and system that generate a prioritized listing of customers by calculating a purchase behavior prediction score, which incorporates payment difference scores and behavior scores derived from various factors such as equity value, incentive-related values, product enhancements, and household demand, to provide a more comprehensive understanding of customer purchasing intentions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing CRM software uses simple data mining methods focusing on financial data, then the system complexity is low and ease of operation is maintained, but the measurement precision of customer purchasing behavior prediction deteriorates
Solution Approach 1:
The patent segments the customer purchasing behavior prediction into multiple independent components: payment difference score calculation, behavior factor analysis, and purchase behavior prediction score generation. Each component processes specific aspects of customer data separately, improving prediction accuracy while maintaining manageable system complexity through modular design.
Solution Approach 2:
The patent transitions from traditional one-dimensional financial data analysis to multi-dimensional analysis by incorporating behavior factors (equity value, incentive-related values, product enhancements, household demand) alongside payment differences. This dimensional expansion enables more comprehensive customer behavior prediction.
2Reliability
If existing software products generate offers based on random assumptions about customer financial status, then the ease of manufacture is maintained, but the reliability of sales lead generation deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where customer behavior factors and purchase history are continuously analyzed to refine payment difference scores and purchase behavior prediction scores. This feedback loop replaces random assumptions with data-driven insights, improving sales lead reliability while systematically processing customer information.
Solution Approach 2:
The patent changes key parameters from simple financial status indicators to composite scores including payment difference scores and purchase behavior prediction scores. These parameter transformations convert raw financial data into meaningful predictive metrics that reliably identify potential sales leads.
3Loss of information
If existing systems only compare payment amounts to determine customer eligibility, then the ease of operation is maintained, but the loss of information about customer decision-making factors increases
Solution Approach 1:
The patent creates a universal analysis framework that handles multiple types of customer data (financial payment information, equity value, incentive preferences, product preferences, household demand) through a unified process. This multi-functional approach preserves comprehensive decision-making information while maintaining consistent analysis methodology.
Solution Approach 2:
The patent performs preliminary analysis of customer behavior factors and payment differences before generating final purchase behavior prediction scores. This preliminary processing organizes and preserves critical decision-making information in structured formats, preventing information loss during subsequent analysis stages.
Data Source
AI summary
There is provided a method of generating on a computer a prioritized listing of customers. The method includes establishing a data communications link to a database including financial payment information related to a financial transaction of an existing vehicle of each customer. The method includes retrieving an existing payment amount based upon the financial payment information. The method includes calculating a new payment amount. The method further includes deriving a payment difference score based upon a difference between the existing payment amount and the new payment amount. The method includes determining a behavior factor. The method includes deriving on a computer a behavior score based upon the behavior factor. The method includes determining a purchase behavior prediction score based upon the payment difference score and the behavior score. The method further includes ranking each customer based upon the determined purchase behavior prediction score. The method further includes generating a prioritized listing using the ranking of each customer.