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

Big data risk analysis method

A risk analysis and big data technology, applied in data processing applications, instruments, finance, etc., can solve problems such as data authenticity and reliability cannot be guaranteed

Inactive Publication Date: 2016-11-16
BEIJING TUOMING COMM TECH
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] Policyholders may deliberately conceal information that is not conducive to themselves (disease history, genetic history, nature of work, etc.), resulting in the authenticity and reliability of the data cannot be guaranteed
Therefore, risk models derived from traditional data clearly have significant holes

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
  • Big data risk analysis method
  • Big data risk analysis method
  • Big data risk analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0032] Such as figure 1 Shown, the process of the present invention is as follows:

[0033] Step (1): On the basis of the existing actuarial model, combined with big data to establish a new model for predicting user risks;

[0034] Step (2): verify the feasibility of the new model;

[0035] Step (3): Determine the relationship between the forecast accuracy rate and the insurance company's compensation rate, and then determine the profit space of the new model.

[0036] The method of combining big data, such as Figure 13 As shown, first, the Hadoop platform is used to complete the preprocessing of the original data and the training of feature engineering, and then the machine learning model is trained using binary classification algorithms such as logistic regression, and finally the AUC method is used to evaluate the model.

[0037] Among them, t...

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 relates to a big data risk analysis method. According to the method, daily behavior habits of an insured person are analyzed by utilizing a machine learning algorithm model in combination with big data, and a possibility that the insured person suffers from a disease or has an accident is predicted, so that a corresponding insurance premium standard is made. Further the feasibility of a new model is studied; first a relational expression of compensation rate and prediction accuracy of the new model is established, a negative correlation of the prediction accuracy and the compensation rate is discovered, and when the prediction accuracy is greater than 50%, the compensation rate of the new model is lower than that of an original model; the model is visually analyzed by using MATLAB; and then the new model is subjected to profitability analysis, a three-dimensional relationship among a discount of a low-risk customer, the prediction accuracy and profits is established, and the profit space increased under the new model is obtained more visually.

Description

technical field [0001] The invention specifically relates to a big data risk analysis method, which belongs to the technical field of big data risk analysis. Background technique [0002] Ebola epidemic, Malaysia Airlines MH370 crash, warehouse bombing in Tianjin, terrorist attack in Paris, France... All kinds of disasters and accidents that continue to appear in human society after entering the 21st century warn us without exception: risks are everywhere, and a A new social form characterized by risks is gradually coming. [0003] Traditional risk assessment methods can no longer meet our needs for risk assessment. Traditional risk assessment has great difficulties in analyzing follow-up data. It cannot be sure that all follow-up data are authentic and reliable, and there will be a large number of Lost to follow-up (lost contact, unobservable outcome, cut-off of a study, etc.), obviously, we can see that it seems unreasonable to count the lost-to-follow-up data as death or...

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): G06Q10/06G06Q40/08
CPCG06Q10/0635G06Q40/08
Inventor 翟玲智陈旭董冠宁常青
Owner BEIJING TUOMING COMM TECH
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