Financial transaction fraud risk finger model smoothing function extraction method

A financial transaction and smoothing function technology, applied in finance, complex mathematical operations, data processing applications, etc., can solve problems such as support, ineffective use, and artificial intelligence models that only accept digital data and do not accept set or text data input, etc., to achieve The effect of good application prospects

Pending Publication Date: 2022-02-25
南京铭诚智科信息技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, many artificial intelligence models only accept numerical data and do not accept set or text data input
Most AI models that accept numerical data input perform well on numerical data input, but cannot accept aggregated or literal data, which account for a large proportion of transactions, so existing techniques cannot Effective use of the above data cannot play a supporting role in the improvement of anti-fraud technology, and there is still room for improvement in the corresponding anti-fraud technology

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
  • Financial transaction fraud risk finger model smoothing function extraction method
  • Financial transaction fraud risk finger model smoothing function extraction method
  • Financial transaction fraud risk finger model smoothing function extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The financial transaction fraud risk index smoothing function extraction method includes two steps: the extraction of the risk index and the establishment of a mathematical formula for the risk index; the extraction of the risk index includes collecting and extracting information including text in the original sample database. Data, calculating the statistical characteristic value of the data in each transaction parameter set, correcting the statistical characteristic value in each transaction parameter set, and judging whether the risk index in each transaction parameter set conforms to a certain mathematical probability distribution of continuous variables in four sub-steps ; The mathematical formula of the risk index includes the establishment of eigenvalue formula, the original fraud risk ratio formula, the logarithmic occurrence ratio formula, the modified smooth formula, and the calibration formula.

[0019] Collecting and extracting data including text in the orig...

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 financial transaction fraud risk finger model smoothing function extraction method comprises two steps of extracting a risk finger model and establishing a mathematical formula of the risk finger model. The extraction of the risk fingerprints comprises the steps of collecting and extracting data including characters in an original sample database; calculating a statistical characteristic value of data in each transaction parameter set, correcting the statistical characteristic value in each transaction parameter set, and judging whether the risk finger model in each transaction parameter set accords with a continuous variable of certain mathematical probability distribution; the mathematical formula of the risk finger model comprises a characteristic value establishing formula, an original fraud risk rate ratio formula, a logarithm occurrence ratio formula, a correction smoothing formula and a calibration formula. The extracted risk fingerprints can be directly or indirectly used for artificial intelligence model input variables for fraud risk assessment, possibility is provided for use of a complex artificial intelligence model, and a favorable guarantee is also provided for training an expandable system model by using mass transaction data.

Description

technical field [0001] The invention relates to the field of anti-fraud technology applied in the financial sector, in particular to a financial transaction fraud risk index smoothing function extraction method. Background technique [0002] At present, financial fraud risk control has entered the era of big data and artificial intelligence. As an important technical link in the process of financial transaction risk control, artificial intelligence models have achieved remarkable results in international and domestic anti-trade fraud struggles. The performance of the artificial intelligence model is highly dependent on the information degree of the input data, and the habitual characteristics of the behavior of both parties in each transaction parameter set (digital set and text data set, such as transaction time, transaction amount, etc.) are the key points of the artificial intelligence anti-fraud model. An original, important and reliable source of information and data. ...

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 & AuthorityApplications(China)
IPC IPC(8): G06F17/18G06Q20/40G06Q40/04
CPCG06F17/18G06Q20/4016G06Q40/04
Inventor金坚徐欣
Owner南京铭诚智科信息技术有限公司