Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A default user probability prediction method based on sparse feature embedding

A sparse feature and probability prediction technology, applied in special data processing applications, data processing applications, resources, etc., can solve problems such as unsatisfactory sparse data processing effects, and achieve benefits for learning and processing, improving processing capabilities, and reducing dimensions Effect

Inactive Publication Date: 2019-06-21
华融融通(北京)科技有限公司
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods are not very effective in processing sparse data.

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
  • A default user probability prediction method based on sparse feature embedding
  • A default user probability prediction method based on sparse feature embedding
  • A default user probability prediction method based on sparse feature embedding

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0060] In this part, the original features obtained through data cleaning in the first step are processed by feature engineering and converted into training data for the model. Firstly, the original features are converted into new features through the traditional feature engineering method, and then part of the sparse features in the new features are converted into one-dimensional variables through the multi-category variable method proposed by the present invention, which can be directly used as the training data of the model. The specific implementation is as follows:

[0061] 2.1 Feature Engineering

[0062] The variables in the original features are subjected to feature extraction and variable derivation according to the time class, amount class, address class, and phone number class. The time field includes authentication time, loan time, shopping time, etc. 00-24:00) and early morning (00:00-6:00), and count the number and proportion of orders in these four time period...

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 a default user probability prediction method based on sparse feature embedding. The method comprises the following steps: firstly, converting original data of a user into variable features, and then mapping multi-class variables in the variable features into a sparse matrix (similar to one-hot processing); And on the basis, mapping the sparse matrix to a probability througha basic decision tree model, and adding the probability as a feature to the model to predict a default user. Compared with the prior art, the default user probability prediction method based on sparse feature embedding has the advantages that the processing capacity of category coding is effectively improved, meanwhile, the dimension of feature space is effectively reduced in the subsequent machine learning process, and learning and processing of a machine learning model are facilitated.

Description

technical field [0001] The invention relates to a method for predicting the probability of defaulting users based on sparse feature embedding, which relates to a user credit risk assessment technology in the financial field, and in particular to a method for predicting the probability of defaulting users in the consumer finance field for asset management companies. Background technique [0002] In recent years, Internet finance companies with P2P lending and consumer finance as their main businesses have emerged, establishing a huge emerging industry in areas that traditional financial industries cannot touch. But at the same time, all kinds of negative news came one after another, casting a shadow over the future of these Internet financial companies. Among them, the risk control capability has always been the lifeblood of these emerging technology financial companies. Only with good risk control technology can it be possible to develop healthily in this wave. Traditional ...

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): G06Q10/06G06Q40/00G06F16/215G06F16/2458
Inventor 后其林李达钟丽莉万谊强仵伟强赖咪
Owner 华融融通(北京)科技有限公司
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
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