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

Method and apparatus for evaluating model interpretation tools

A technology for evaluating models and models, applied in the field of machine learning, to solve problems such as the lack of multiple model interpretation tools

Active Publication Date: 2022-03-01
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is still no method that can be applied to multiple model interpretation tools 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
  • Method and apparatus for evaluating model interpretation tools
  • Method and apparatus for evaluating model interpretation tools
  • Method and apparatus for evaluating model interpretation tools

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Embodiments of this specification will be described below with reference to the accompanying drawings.

[0037] figure 1 A schematic diagram of a system 100 for evaluating model interpretation tools according to an embodiment of the present specification is shown. like figure 1 As shown in , the system 100 includes a sample processing unit 11 , a black box model 12 , a model interpretation tool 13 and a calculation unit 14 . The black box model 12 is a non-self-explanatory model that is expected to be explained by the model interpretation tool 13, such as various complex neural network models, etc. The neural network model cannot The importance of sample features is explained by its individual parameters or network structure. The black box model 12 can be trained through multiple training samples related to a specific business, so as to become a business processing model, such as a risk control model. For example, the specific service is to classify users on the net...

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

Embodiments of this specification provide a method and device for evaluating a model interpretation tool, the method is performed based on a first model and a plurality of first training samples obtained in advance for the first model, including: from the plurality of features Selecting n features as n selected features; replacing feature values ​​of features other than the n selected features in each of the first training samples with other values ​​to obtain a plurality of second training samples; Using the plurality of second training samples to train the first model to obtain a first model having a first set of parameters; based on the plurality of second training samples and the first set of parameters, obtained by a model interpretation tool An importance ranking of the plurality of features; determining a recall of the top n features of the importance ranking relative to the n selected features for use in evaluating the model interpretation tool.

Description

technical field [0001] The embodiments of this specification relate to the technical field of machine learning, and more specifically, to a method and device for evaluating model interpretation tools. Background technique [0002] Machine learning is currently being used in various fields such as retail, technology, healthcare, science, and many more. A machine learning model essentially fits a complex function to the relationship between the data and the target. The machine learning model is very different from some simple rules. The rules clarify the relationship between data and targets, but the machine learning model is a black box with only input and output, and does not understand the internal mechanism. In some fields, especially in finance, such as insurance, banking, etc., data scientists often end up having to use more traditional and simpler machine learning models (linear models or decision tree models). However, although this type of simple model can provide a...

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 Patents(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/217
Inventor 方军鹏唐才智
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
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