Skip to main content

2021 | OriginalPaper | Buchkapitel

10. Bairong Zhixin: Big Data and Credit System Construction

verfasst von : Bao Sun

Erschienen in: Inclusive Finance in China

Verlag: Springer Singapore

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Finance, particularly microfinance, proposes great demands for credible third-party credit evaluation services. However, the backward social credit system in China is far from meting the demands. Such new technologies as the Internet, e-commerce and big data provide a new opportunity for the rapid development of the credit industry. Bairong Zhixin has established an effective risk assessment model depending on its own big data technology and online and offline multi-dimensional data from retail, social activities, media, aviation, education, operators and brands etc. As proved by the case of Bairong Zhixin, big data credit assessment technology can improve traditional credit risk evaluation based on the special “dynamic information” mechanism, expand the coverage and relieve information asymmetry in financial activities. By applying big data technology to credit rating, it will innovate and advance the industry and play an extremely important role in facilitating the social credit system construction in China.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Fußnoten
1
Character, capacity, capital, collateral and condition.
 
2
Personal identifiable information, PII, refers to the user’s personal information including name, ID card, mobile phone number, e-mail and other information that helps identifying a specific person in reality.
 
3
Cookie is the data stored by certain websites in users’ local terminals (often encrypted) for identifying users’ identification and tracking users’ dialogues.
 
4
IMEI, International Mobile Equipment Identity, is the unique identification number of a mobile phone. Every mobile phone will be assigned with an IMEI during production.
 
5
Exploratory data analysis includes univariable analysis, bivariable analysis, correlation analysis, cross validation and outlier analysis. The univariable analysis involves such continuous variables as observed data, mean value, standard deviation, skewness, missing data and mode etc. as well as categorical variables including frequency, relative frequency, cumulative frequency and cumulative relative frequency of each category. Bivariable analysis is used to predict the trend of variables and bad debt ratio. Correlation analysis calculates the Pearson correlation coefficient among continuous variables as the index to measure the correlation of continuous variables. These weak variables will be subject to cross validation to determine that whether they can be applied to valuate credit risk. Finally, the outlier analysis is performed and outliers and removed.
 
6
The KS test is a statistical method adopted to conduct statistical analysis over a group of data. It compares the data for statistical analysis to another group of standard data to obtain the deviation between the data for analysis and the standard data. Generally in a KS test, we shall first calculate the cumulative distribution functions of the two groups of observed data that need to be compared, and then calculate the maximum value D of the absolute difference between the two cumulative distribution functions. Then by checking the table, we will determine whether the value D falls into the corresponding confidence interval as required. If yes, it proves that the tested data comply with the requirements; and vice versa. In the model of Bairong Zhixin, the KS value is defined as the maximum difference between the cumulative “bad” customers proportion and the cumulative “good” customers proportion when all applicants in the sample are sorted by the score from low to high.
 
7
The banking industry universally uses KS value to judge the effect of the model in distinguishing good from bad customers. The higher KS value suggests the better performance of the model.
 
8
The overall matching rate means the proportion of customers who have at least one of the certificate number, mobile phone number and e-mail address registered at the P2P platform consistent with the data in Bairong Financial Service database in the total number of platform customers.
 
9
Dean of Renmin Business School, and professor and doctoral supervisor of the Department of Management Science and Engineering, Renmin University of China.
 
Literatur
Zurück zum Zitat An Jian, Liu Shiyu, Pan Gongsheng, Interpretation of Regulations on the Administration of Credit Industry, Beijing: China Democracy and Legislation Publishing House, 2013. An Jian, Liu Shiyu, Pan Gongsheng, Interpretation of Regulations on the Administration of Credit Industry, Beijing: China Democracy and Legislation Publishing House, 2013.
Zurück zum Zitat Zhang Shaofeng, Big Data Risk Modelling Combining Online and Offline Data, “China Credit Reference”, 2014, 11. Zhang Shaofeng, Big Data Risk Modelling Combining Online and Offline Data, “China Credit Reference”, 2014, 11.
Metadaten
Titel
Bairong Zhixin: Big Data and Credit System Construction
verfasst von
Bao Sun
Copyright-Jahr
2021
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-16-1788-1_10