Location

Hilton Waikoloa Village, Hawaii

Event Website

http://www.hicss.hawaii.edu

Start Date

1-4-2017

End Date

1-7-2017

Description

Smart city construction emphasizes building an effective whole social credit system, promoting the construction of government integrity, business integrity, social integrity and public confidence in the judiciary. For credit risk has become an important assessment. Meanwhile, administration credit system is one of three major data. It proposes unified credit discipline and warning regulatory purposes, led by the government and its main functions, taken governmental data as the main basis. Accordingly, the paper constructs Corporate Dishonest Credit Executed (CDCE) Risk Assessment Model, based on governmental data. The model uses a set of urban enterprise data, selecting the explanatory variables from five aspects, administrative punishment, innovation, credit information, credit situation, and social responsibility, to screen CDCE Logit regression, to filter out and find out those variables which are significantly predicted effects for CDCE risk. And then construct a Logit regression model with the above selected variables. The experimental results and comparison of practical applications in China, we found that the model promises to higher business risk identification accuracy for CDCE. The model has a higher applied value and developmental prospects.

Share

COinS
 
Jan 4th, 12:00 AM Jan 7th, 12:00 AM

Model Design and Implementation of Enterprise Credit Information Based On Data Mining

Hilton Waikoloa Village, Hawaii

Smart city construction emphasizes building an effective whole social credit system, promoting the construction of government integrity, business integrity, social integrity and public confidence in the judiciary. For credit risk has become an important assessment. Meanwhile, administration credit system is one of three major data. It proposes unified credit discipline and warning regulatory purposes, led by the government and its main functions, taken governmental data as the main basis. Accordingly, the paper constructs Corporate Dishonest Credit Executed (CDCE) Risk Assessment Model, based on governmental data. The model uses a set of urban enterprise data, selecting the explanatory variables from five aspects, administrative punishment, innovation, credit information, credit situation, and social responsibility, to screen CDCE Logit regression, to filter out and find out those variables which are significantly predicted effects for CDCE risk. And then construct a Logit regression model with the above selected variables. The experimental results and comparison of practical applications in China, we found that the model promises to higher business risk identification accuracy for CDCE. The model has a higher applied value and developmental prospects.

http://aisel.aisnet.org/hicss-50/da/decision_support_for_smart_cities/4