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

P2P (peer-to-peer) network lending risk prediction system based on text analysis

A P2P network and risk prediction technology, which is applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of low prediction accuracy of the risk prediction system, improve overall operational efficiency, reduce audit time, and accuracy Improved effect

Active Publication Date: 2015-05-13
哈尔滨工业大学人工智能研究院有限公司
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention solves the problem that the prediction accuracy rate of the existing risk prediction system is not high

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
  • P2P (peer-to-peer) network lending risk prediction system based on text analysis
  • P2P (peer-to-peer) network lending risk prediction system based on text analysis

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0014] Specific implementation mode one: combine figure 1 To describe this embodiment,

[0015] The platform data collection module is used to automatically collect user data and transaction data in the P2P network lending platform, including user basic data, user credit data, loan list data, loan description text, and loan repayment;

[0016] The text feature extraction module is used to obtain the "loan description text" in the platform data collection module and perform word segmentation and remove words without actual meaning according to the stop word list, and is responsible for extracting the semantic features contained in the loan description text, including emotion feature S, theme feature T, and readability feature R;

[0017] Risk prediction model building and training modules, used to build and train risk prediction models;

[0018] The risk prediction module is used to predict and output the risk situation of the new borrowing list.

specific Embodiment approach 2

[0019] Specific implementation mode two: this implementation mode

[0020] Described text feature extraction module comprises:

[0021] The word segmentation sub-module is used to obtain the "loan description text" in the platform data collection module and perform word segmentation and remove words without actual meaning according to the list of stop words;

[0022] The emotional feature S extraction and storage sub-module is used to extract and store the emotional feature S of the loan description text;

[0023] The topic feature T extraction and storage sub-module calculates the topic probability distribution P (topic | text) in each loan description text through the LDA topic generation model, and stores it as the topic feature T of the loan description text;

[0024] The readability feature R extraction and storage sub-modules first count the number of occurrences of each word in all loan description texts, and then count the words that appear in the current loan descrip...

specific Embodiment approach 3

[0026] Specific implementation mode three: this implementation mode, in combination with figure 2 To describe this embodiment,

[0027] The emotional feature S extraction submodule includes

[0028] The artificial sentiment labeling sub-module randomly extracts the loan description text and outputs and displays it for users to carry out artificial sentiment labeling: commendatory, neutral and derogatory, marked with 1, 0 and -1 respectively; and the loan description text that has been artificially labeled Divided into emotional labeling training set and emotional labeling test set;

[0029] The computer emotion classification sub-module extracts the emotional labeling training set data in the artificial emotional labeling sub-module, and calculates three emotional categories of 1, 0 and -1 (commendative, neutral and derogatory) according to the artificial emotional labeling of the emotional labeling training set The number of occurrences of each word set in the set; on this...

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 relates to P2P network lending risk prediction systems, in particular to a P2P network lending risk prediction system based on text analysis. The P2P network lending risk prediction system based on text analysis comprises a platform data acquisition module, a text feature extraction module, a risk prediction model building and training module and a risk prediction module. The text feature extraction module is used for performing word segmentation on a loan description text acquired by the platform data acquisition module, removing words having no actual meaning according to a stop word list and extracting emotional characteristics S, theme characteristics T and readability characteristics R in the loan description text; and then a risk prediction model is built and trained; finally the emotional characteristics S, the theme characteristics T and the readability characteristics R in the new loan list and user basic data, user credit data and loan list data in the platform data acquisition module are used as input variables to be input into the risk prediction model to obtain a risk prediction result. The P2P network lending risk prediction system based on text analysis is applicable to P2P network lending risk prediction.

Description

technical field [0001] The invention relates to a risk prediction system for P2P network lending. Background technique [0002] With the in-depth application of Internet technology in the financial field, a financial model that realizes direct lending between individuals through the Internet has emerged, called P2P network lending (peer-to-peer lending). P2P network lending operators provide network platforms (such as Paipaidai, Renrendai, etc.) to match borrowers and lenders to conclude a transaction. Borrowers can fill in personal information on the platform, explain the reasons for borrowing, generate a list of loans and wait for investors to make bidding selections. Investors can decide whether to bid according to the loan-related information provided by the borrower. As a supplement to the traditional financial model, P2P online lending can further meet the investment and financing needs of long-tail users. [0003] However, due to the imperfection of the domestic cr...

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): G06Q40/08G06F17/27
Inventor 叶强郭雷张紫琼张自立
Owner 哈尔滨工业大学人工智能研究院有限公司
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