Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Vehicle insurance renewal prediction method and system

A forecasting method and forecasting system technology, applied in the computer field, can solve the problem of high accuracy, and achieve the effects of high stability of accuracy, high volatility of accuracy, and improved accuracy

Pending Publication Date: 2019-07-05
上海赢科信息技术有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method and system for auto insurance renewal prediction in order to overcome the defects in the prior art that the prediction of the customer's renewal intention cannot satisfy the high accuracy rate and relatively stable accuracy rate at the same time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vehicle insurance renewal prediction method and system
  • Vehicle insurance renewal prediction method and system
  • Vehicle insurance renewal prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] This embodiment provides a method for predicting auto insurance renewal. A renewal prediction model is established for each dealer, which avoids the large fluctuations in the accuracy of the prediction model caused by the huge difference in the customer composition data structure of different dealers; The small sample data of a single dealer is complemented, which greatly improves the accuracy of the prediction, and the accuracy rate is highly stable.

[0043] Such as figure 1 As shown, the renewal prediction method of the auto insurance of the present embodiment includes the following steps:

[0044] Step 110, acquiring the policy data group of the target object.

[0045]In step 110, the target object is, for example, a dealer. In step 110, the policy data sets of all customers who purchase auto insurance at a certain dealer are obtained. Wherein, each group of insurance policy data includes: vehicle owner data, vehicle data and insurance application data. The owner...

Embodiment 2

[0065] This embodiment provides an auto insurance renewal prediction system, which establishes a renewal prediction model for each dealer, avoiding the large fluctuations in the accuracy of the prediction model due to the huge difference in the customer composition data structure of different dealers; The small sample data of a single dealer is complemented, which greatly improves the accuracy of the system prediction, and the system is relatively stable.

[0066] Such as figure 2 As shown, the auto insurance renewal prediction system of this embodiment includes: a data acquisition module 1 , a data completion module 2 , a calculation module 3 and a model training module 4 .

[0067] The data acquisition module 1 is used to acquire multiple sets of insurance policy data sets of the target object. The target object is, for example, a dealer, and the data acquisition module 1 obtains the policy data groups of all customers who purchase auto insurance at a certain dealer. Wher...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a vehicle insurance renewal prediction method and system. The insurance renewal prediction method comprises the steps of acquiring the multiple insurance policy data sets of atarget object; carrying out missing data completion processing on each insurance policy data group; calculating an importance proportion of each parameter in the insurance policy data set after data completion by using an XGBoost model; using a plurality of parameters with the highest importance proportion as training samples to train an XGBoost model, and obtaining an insurance renewal predictionmodel, wherein the input parameters of the renewal prediction model comprise a plurality of parameters with the highest importance proportion, and the output parameters comprise renewal intention scores. According to the invention, one renewal prediction model is established for each dealer, so that the large fluctuation of the accuracy rate of the prediction model caused by the huge difference of customer composition data structures of different dealers is avoided; small sample data of a single dealer is complemented, so that the prediction accuracy is greatly improved, and the accuracy andthe stability are high.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a small-sample-based auto insurance renewal prediction method and system. Background technique [0002] How to identify target customers with high intentions to renew insurance from the total number of customers, and then deploy manpower and resources accordingly to improve the efficiency of insurance specialists, which is conducive to improving customer experience and overall renewal rate. Among them, how to effectively and accurately predict renewal customers is the key. The existing technology provides some mathematical models to only predict renewal customers, but this attribute module is limited to the quality and quantity of data, which has certain limitations. Specifically, due to the small amount of data on car owners of a single dealer, Moreover, most of the customer information is manually entered by the renewal specialists, and the quality of the data is uneven, res...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q40/08G06K9/62G06F17/18
CPCG06Q10/04G06Q40/08G06F17/18G06F18/2148
Inventor 张伟杨治
Owner 上海赢科信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com