Title:
|
RESEARCH ON THE REDUCTION OF HUMAN RESOURCES COST BY DATA MINING TECHNOLOGY- A CASE STUDY OF GOVERNMENT SOCIAL INSURANCE |
Author(s):
|
Kuo-chung Lin , Ching-long Yeh , Meng-jong Kuan |
ISBN:
|
978-972-8924-97-3 |
Editors:
|
Hans Weghorn and Pedro Isaías |
Year:
|
2009 |
Edition:
|
V II, 2 |
Keywords:
|
20/80 principle, data mining, public insurance |
Type:
|
Short Paper |
First Page:
|
207 |
Last Page:
|
211 |
Language:
|
English |
Cover:
|
|
Full Contents:
|
click to dowload
|
Paper Abstract:
|
In respect of the frequent fraud cases of social insurance undertaken by government organizations, the inspection
procedure usually relies on experts experience for verification and experienced personnel in charge for checking.
However, due to the heavy work load and the insufficiency of manpower and experience, the ratio of miscarriages of
justice is high, leading to improper settlement of claims and the waste of social resources.
This thesis takes advantage of data-mining technology to design models and find out cases requiring for manual
inspection so as to save time and manpower. In this paper, six models are designed. By the analysis of the 20/80 principle
and the coverage and accuracy ratio, a great number of periodic data are fed back to the data-mining models after
repetitive verification. Then through continuous revision, the best solution can be found out. During the research, it is
discovered that the 20/80 principle can be applied to revise data-mining models via continuous and repeated verification
so as to screen the largest percentage of questionable cases with the smallest sample size and to considerably reduce time
and labor input in the inspection procedure.
Also, it is discovered that to integrate the data-mining technology and feed back to different business stages so as to
establish early warning system will be an important topic for the insurance system of government organizations in the
future. Meanwhile, as the information acquired by data-mining needs to be stored and the traditional database technology
has limitations, the thesis explores the ontology framework to be set up by semantic network technology in the future in
order to assist the storage of knowledge gained by data-mining. |
|
|
|
|