The use of infection models in accounting and crediting

Recently one of the main directions of data mining is the study and use of network data. Our research is concentrated on the network data about the links of big and medium size of companies that can be deduced from the bank transactions. The main goals are to develop models to predict churn and bank...

Full description

Saved in:
Bibliographic Details
Main Authors: Csernenszky András
Kovács Gyula
Krész Miklós
Pluhár András
Tóth Tamás
Format: Article
Published: 2010
Series:Proceedings of the Challenges for Analysis of the Economy, the Businesses, and Social Progress : International Scientific Conference Szeged, November 19-21, 2009
Kulcsszavak:Matematikai modell, Statisztikai módszer - adatelemzés
Online Access:http://acta.bibl.u-szeged.hu/57828
Description
Summary:Recently one of the main directions of data mining is the study and use of network data. Our research is concentrated on the network data about the links of big and medium size of companies that can be deduced from the bank transactions. The main goals are to develop models to predict churn and bankruptcy. We implement the Domingos-Richardson cascade model, and for the parametrization and evaluation we use the database of the OTP Bank. The results suggest that the developed system is capable of supporting a wide range of applications of network problems such as churn, bankruptcy, campaign management, information diffusion etc.
Physical Description:617-623
ISBN:978-963-06-9558-9