Dealer Selection System Using Logistic Regression Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current online commerce systems lack effective methods for filtering and presenting sales outlets to users and dealers, leading to overwhelming amounts of irrelevant data and inefficient resource allocation, as they do not accurately match users with dealers based on likelihood of successful transactions.
Innovation Solution
A system utilizing a binary choice logistic regression model to rank dealers based on user characteristics and dealer features such as pricing, proximity, historical performance, and market share, predicting the likelihood of a sale and presenting only the most likely candidates to both users and dealers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all possible dealers are listed to users with sorting options, then users have access to complete information, but users are overwhelmed by vast amounts of data and spend excessive time searching
Solution Approach 1:
The patent extracts and highlights only the most relevant dealer characteristics based on user preferences and historical data, separating essential information from irrelevant details. This allows users to quickly identify suitable dealers without being overwhelmed by complete but unnecessary information.
Solution Approach 2:
The system dynamically changes the presentation parameters of dealer information based on user behavior, preferences, and historical transaction data. By adjusting which parameters are displayed and their priority, the system optimizes the balance between information completeness and search efficiency.
2Quantity of substance
If dealers receive all incoming leads without filtering, then dealers have maximum potential customers, but resources are wasted pursuing low-probability leads
Solution Approach 1:
The system performs preliminary filtering and scoring of leads before they are assigned to dealers. By pre-evaluating lead quality based on user characteristics, dealer compatibility, and historical data, the system ensures dealers receive only high-potential leads, maximizing their productivity.
Solution Approach 2:
The patent replaces manual lead evaluation with an automated computational system that uses algorithms to assess lead quality. This substitution of mechanical human judgment with an automated system enables efficient processing and scoring of large numbers of leads based on multiple parameters.
3Device complexity
If dealer selection is based on simple criteria like distance or price, then the system is easy to implement, but the accuracy of matching users with suitable dealers is low
Solution Approach 1:
The patent creates a universal scoring system that integrates multiple selection criteria (distance, price, historical performance, user preferences) into a single comprehensive metric. This multi-functional approach allows the system to consider various factors without increasing operational complexity, as all criteria are processed through a unified algorithm.
Solution Approach 2:
The system combines multiple selection parameters into a composite scoring mechanism, analogous to composite materials. By integrating diverse factors (geographic, financial, behavioral) into a unified dealer score, the system achieves high matching accuracy while maintaining implementation feasibility through a structured framework.
Data Source
AI summary
Systems, methods and computer program products for selecting dealers based on characteristics of the dealers and the user. A vehicle data system collects dealer location and historical transaction data from external data sources and generates and stores an eligibility table that identifies a set of eligible dealers for each combination of user location and vehicle make. Eligible dealers are determined from the eligibility table using a location and vehicle make identified from a user request. Scores are determined for each eligible dealer based on a dealer scoring model using a binary choice model in the form of a logistic regression of market share, inventory, close rate, price and distance, and dealers are ranked by these scores. A presentation of dealers selected by rank and by closest location to the user is generated and provided to the user via an interface running on a computing device.