User service security comprehensive risk assessment method based on combined weighting
A technology that combines empowerment and comprehensive risk, applied in data processing applications, instruments, character and pattern recognition, etc., can solve the problems of low risk differentiation ability, high overall risk, overlapping credit scores, etc., and achieves an intuitive security risk level evaluation system. , the use of promising effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] A method for evaluating the comprehensive risk of user business security based on combined empowerment, the specific steps are as follows:
[0030] Step 1, data processing: perform frequency statistics, proportion calculation, and labeling of the original data to form preliminary indicator variables. The source of the original data is multi-dimensional data extracted from the data warehouse, including business data, risk control log data, and SDK collection. Device data, IP data, etc.;
[0031] Step 2, risk indicator screening: screening risk indicators from the two aspects of differentiation and similarity;
[0032] Step 3, calculating the weight coefficient of single-method weighting: using the subjective weighting method and the objective weighting method to generate weight coefficients respectively;
[0033] Step 4, solving the combined weighting weight of multiple weighting methods, and calculating the comprehensive risk score of each user.
Embodiment 2
[0035] A method for evaluating the comprehensive risk of user business security based on combined empowerment, the specific steps are as follows:
[0036] Step 1, data processing: Perform frequency statistics, proportion calculation and labeling on the original data to form preliminary indicator variables. The numerical data in the original data should be standardized according to the meaning of the indicators. Standardization includes positive standardization, negative Normalization towards normalization and interval type; assuming v ij Indicates the index value of the j-th dimension variable of user i, the training set sample size is n, and the standardized index value is x ij . Indicators that are negatively correlated with user risk can be positively standardized, and the calculation method is as follows: Indicators that are positively correlated with user risk can be negatively standardized, and the calculation method is as follows: When the value of the variable is ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


