SHAP feature attribution method, device and equipment and readable storage medium

A technology for sample characteristics and data interpretation, applied in instrumentation, finance, calculation models, etc., can solve problems such as low model interpretation efficiency

Pending Publication Date: 2020-06-26
WEBANK (CHINA)
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of this application is to provide a SHAP feature attribution method, device, equipment and readable

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
  • SHAP feature attribution method, device and equipment and readable storage medium
  • SHAP feature attribution method, device and equipment and readable storage medium
  • SHAP feature attribution method, device and equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0071] It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

[0072] An embodiment of the present application provides a SHAP feature attribution method, and the SHAP feature attribution method is applied to the driver. In the first embodiment of the SHAP feature attribution method of the present application, refer to figure 1 , the SHAP feature attribution method includes:

[0073] Step S10, obtaining the data to be interpreted, and distributing the data to be interpreted to the execution end associated with the driving end;

[0074] In this embodiment, it should be noted that the data to be explained includes one or more samples to be explained, the samples to be explained include one or more sample features, wherein, in each sample to be explained, each Each of the sample features corresponds to a sample feature value, and the execution end includes an executor of ...

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 an SHAP feature attribution method, device and equipment and a readable storage medium. The SHAP feature attribution method comprises the steps: obtaining data to be interpreted, distributing the to-be-interpreted data to an execution end associated with the driving end; broadcasting a preset to-be-interpreted model to the execution end, enabling the execution end to calculate marginal benefit expectations and label expected values corresponding to the sample features in the to-be-interpreted data in parallel based on the to-be-interpreted model; and receiving each marginal benefit expectation and the label expected value fed back by the execution end, and calculating an SHAP result corresponding to the to-be-interpreted data based on each marginal benefit expectation and the label expected value. The technical problem that the model interpretation efficiency based on the SHAP is low is solved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence of financial technology (Fintech), in particular to a SHAP feature attribution method, device, equipment and readable storage medium. Background technique [0002] With the continuous development of financial technology, especially Internet technology and finance, more and more technologies (such as distributed, blockchain, artificial intelligence, etc.) Requirements, such as the distribution of corresponding to-do items in the financial industry also have higher requirements. [0003] With the continuous development of computer software and artificial intelligence, the application of machine learning has become more and more extensive, and a series of high-performance machine learning models have also been developed, such as random forests, gradient boosting trees, deep learning, etc., but these The internal principles of machine learning models are difficult to underst...

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
IPC IPC(8): G06N20/00G06Q40/00
CPCG06N20/00G06Q40/00
Inventor 卓本刚黄启军唐兴兴林冰垠
Owner WEBANK (CHINA)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap