The National Centre for Text and Data Mining (NCTDM) 

 

 

Mission Statement

To advance the processes of automated discovery of knowledge in data.

Objectives

The research and development in  Text & Data Mining of: 

- models, methodologies and tools for a broad range of user communities.

- generic resources that can be used by users to enhance data mining techniques

- data mining techniques that utilise external knowledge resources.

- software engineering architectures and methods.

Members

Sanjay Chawla

Jon Patrick

John Roddick

Geoff Webb

Staff

Dr James Farrow

 

 

Partners

School of Information Technologies, University of Sydney

Department of Computer Science, Engineering & Mathematics,  Flinders University

Faculty of Information Technology, Department of Computer Science, Monash University

 

 

Collaborating Organisations

DSTO

Sydney West Area Health Service 

Blacktown-MtDruitt Hospital

Royal Prince Alfred Hospital 

Concord Hospital

Family Medicine Research Centre

Southwest Area Pathology Services 

Monash Biology

State Library of Victoria

National Library of Australia

Monash Biology

Collaborators

Prof Iain McCalman, University of Sydney

Prof Graeme Davison, Monash University

Prof Stuart Mc Intyre, Melbourne University

Prof John Hurst, Latrobe University

Dr John Shipp, University of Sydney

Dr Ian Johnson, University of Sydney

Dr Deborah Mitchell, ANU

Projects

Black Box Computational Modelling Methodology

Information extraction from clinical notes

Ontology design and minimisation for natural language processing

Discovering justified knowledge from data

Learning Complex Conditional Probabilities from Data

Computational analysis of molecular coevolution in families of proteins

Methods and software for efficiently solving the transportation crewing problem

Integrated Intelligent Decision Support for Field Design and Management of Census Operations in Australia

Intelligent Collaborative Care Management

===

Data Mining Links

The technology of Text and Data Mining is used in a great variety of disciplines. This is a list of a number of papers and descripton of successful projects and usages.

(1) http://www.the-data-mine.com/bin/view/Misc/ApplicationsOfDataMining

List of different areas of data Mining applications and links to them. But you need to register if you want to see something.

(2) http://www.twocrows.com/applics.htm

List of data mining application areas. Two crows consulting.

(3) http://www.kdnuggets.com/polls/2005/successful_data_mining_applications.htm

Poll about *industries/fields where **data mining was **/s/**/uccessfully/ applied *

Links to some books. The indexes give long lists of different applications where data mining can be used.

(4)http://www-users.cs.umn.edu/~kumar/kluwer-book/dm.htm

Link to book: *Data Mining for* *Scientific and Engineering Applications

*The index can give an idea of different application areas, different methods...

Image collections, Astronomical data, Bioinformatics, Turbulent flows, failure prevention in event sequences,...

(5) http://eu.wiley.com/WileyCDA/WileyTitle/productCd-0471656054,descCd-tableOfContents.html

Link to index of the book: Next Generation of Data-Mining Applications.

Different application areas: wafer fabrication, damage detection, customer relationship management, automatic evaluation of sales opportunity, earth science, Egeria densa detection in digital imagery, gene mapping, medical domain, operational crime fighting...

Deeper description of some applications

(6) http://www.spss.com/data_mining/

SPSS Introduction to importance of Data Mining + 4 examples:

`- Boost sales by 50 percent and reduce marketing costs by 30 percent

- One of the Japan's top personal computer and software retailers obtained triple online profits by improving personalization features. They built an engine that recommends appropriate products based on customers' profiles.

  - Standard Life, one of the world's leading mutual financial services companies obtained secure an additional $50 million in revenue by using an accurate propensity model to target offers.

  - BT (British Telecommunications) needed to identify customers' propensity to purchase and calculate their likely comparative value once they became customers. They improvee the response rate of direct mail campaigns by 100 percent.

Document Library

About the NCTDM