New technology in knowledge discovery and data mining (KDD) make it possible to extract valuable information from operational data. Private businesses already use the technology for better management, planning, and marketing. Social welfare government agencies have a wealth of information about the experiences of families and individuals that are the most needy in our society in their administrative databases. These data too can be mined and analyzed with proper application of KDD technology. Such social science research could be priceless for better welfare program administration, program evaluation, and policy analysis. In this paper, we discuss a successful case study involving research in computer science as well as social welfare. In a long standing collaboration between the North Carolina DHHS and the University of North Carolina, we have (1) successfully built a longitudinal information system that tracks the experiences of families and individuals on welfare in NC since 1995 (2) developed a dynamic website reporting on the various aspects of the welfare program at the county level in order to assist county staff in the administration of the welfare program and (3) developed a new method to analyze sequential data, which can detect common patterns of welfare services given over time.
[1]
FayyadUsama,et al.
The KDD process for extracting useful knowledge from volumes of data
,
1996
.
[2]
Susan Paulsen,et al.
Comparative Study of Sequential Pattern Mining Frameworks Support Framework vs . Multiple Alignment Framework
,
2002
.
[3]
Jian Pei,et al.
ApproxMAP: Approximate Mining of Consensus Sequential Patterns
,
2003,
SDM.
[4]
Gregory Piatetsky-Shapiro,et al.
The KDD process for extracting useful knowledge from volumes of data
,
1996,
CACM.
[5]
Simon Parsons,et al.
Principles of Data Mining by David J. Hand, Heikki Mannila and Padhraic Smyth, MIT Press, 546 pp., £34.50, ISBN 0-262-08290-X
,
2004,
The Knowledge Engineering Review.
[6]
Ramakrishnan Srikant,et al.
Mining sequential patterns
,
1995,
Proceedings of the Eleventh International Conference on Data Engineering.