Browse Prior Art Database

System to evalute trader credit rating via social data in C2C e-commerce

IP.com Disclosure Number: IPCOM000247108D
Publication Date: 2016-Aug-05
Document File: 4 page(s) / 63K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article describes how to leverage social data from both buyer and seller to generate the credit value. The value is very useful and important to predict the trade success before trade. In this articel, we provide a new method to evalute the credit value by social dynamic data, social static data, location base data and so on.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 01 of 4

System to evalute trader credit rating via social data in C2C e-commerce

Customer to customer trading exists very high risk, like one of the most big customer to customer social platform, connect seller and buyer together through building network community, and afford product display service for seller, then buyer can choose the products they interested in and bid to buy them. according to static data

Our disclosure discover a method to evaluate the credit data between seller and buyer via both traders' social data in Customerto Customer (C2C) e-commerce
the social data include but not limit to social static data or social activity data
the evaluation system dynamically calculate the credit data between any corresponding seller and buyer
the output credit data can be input into C2C e-commerce system for system and end user leverage

This system evaluates the credit value between one seller and one buyer by social data, include:
A. Social Dynamic Data, these data includes but not limited
1) Social reputation from social network, like V mark, endorse, verified public figure, and etc.

2) Social activity , interest part, catalog, experience, expertise
B. Social Static Data which not related to user social interaction
1)Company
2)education
3)finance situation
4)industry average salary
5)age
etc
C. Location Base Data, which includes end user social activity location, like daytime work location, travel location, community location, other activity location etc

Above data are very important to evaluate credit rating of trader. For example,
the seller and/or the buyer have good reputation in social community, traders should get higher credit rating
the seller and the buyer are have close relationship, like work in same company, traders should get hgiher credit rating the seller and/or the buyer have good education or finance situation, traders should get higher credit rating
the seller and buyer are expertise in trade production field, they should get higher credit rating
etc

Following chart shows how our system works. This system have two models: Data Collection Model and Credit Rating Evaluation Model.
1) Data Collection model

1



Page 02 of 4

This model focus on collecting both sellers' and buyers' above social data from social media, like social network, map service, etc.


2) Credit Rating Evaluation Model


This is the model, which leverage social data from the specific seller and buyer, and then generate the credit rating for thespecific pair of seller and buyer . Different pair may get the different credit rating according to their social data difference.

Here is example of how to calculate the credit rating:

The credit value for company = WeightCompany * CompanyVa...