(text)
PAKDD-98, Call for Participation: 2nd Pacific-Asia Conf. on
Knowledge Discovery and Data Mining,
Melbourne, Australia, April 15-17, 1998, http://www.sd.monash.edu.au/pakdd-98
(text)
Saso Dzeroski, Analysis of environmental data with ML
17.-20. March 1998, Ljubljana, Slovenia http://www-ai.ijs.si/SasoDzeroski/aep/aep.html
--
latest news, publications, tools, meetings, and other relevant items
in the Data Mining and Knowledge Discovery field.
KD Nuggets is currently reaching over 4600 readers in 60+ countries
twice a month.
Submissions relevant to data mining and knowledge discovery are welcome
and should be emailed to gps
in ASCII text
or HTML format.
A submission should have a subject line which clearly describes
what is it about. Please keep calls for papers and meeting announcements
short (50 80-character lines or less), and provide a web site for details.
Submissions may be edited for size.
Back issues of KD Nuggets, a catalog of data mining tools
('Siftware'), pointers to data mining companies, relevant websites,
meetings, and more is available at KDNuggets Directory at http://www.kdnuggets.com/
********************* Official disclaimer ***************************
All opinions expressed herein are those of the contributors and not
necessarily of their respective employers (or of KD Nuggets)
*********************************************************************
~~~~~~~~~~~~ Quotable Quote ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
From Salon http://www.salon1999.com/
'Haiku Error Messages' contest.
Three things are certain:
Death, taxes, and lost data.
Guess which has occurred.
(thanks to Mark Kuznetsov) Previous1NextTop
From: Gregory Piatetsky-Shapiro gps
Date: Mon, 16 Feb 1998 10:13:34 -0500
Subject: KDD-98 Preview and a Final Call For Papers
Web: http://www-aig.jpl.nasa.gov/public/kdd98/
Business and scientific endeavors now routinely gather large
quantities of data that can help with understanding critical problems
and with making strategic and tactical decisions. However, manual
analysis becomes difficult as databases grow, and techniques for
discovering and extracting knowledge automatically become necessary.
The Fourth International Conference on Knowledge Discovery and Data
Mining (KDD-98) will address the science and technology of automated
discovery, drawing from the fields of statistics, databases, machine
learning, data visualization, high performance computing, knowledge
acquisition, and knowledge-based systems.
Besides scientific and technical contributions from the latest
research and applications, this year's program will also feature
tutorials (free to all registered attendees) by leading experts,
demonstrations by leading tool vendors, and invited talks summarizing
the state of the art and looking forward to the future.
The field's interdisciplinary nature facilitates the cross-fertilization
of ideas, and this summer KDD-98 will be co-located with the 24th
International Conference on Very Large Databases (VLDB-98).
The KDD-98 program promises many opportunities for exciting
interactions--but to fulfill that promise we need you! Please join us
this August in New York City.
KDD-98 Final Call for Papers:
We encourage the submission of both fundamental and applied research
papers on algorithms for discovery and for extracting knowledge from
data, as well as papers on other facets of the knowledge discovery
process (representation, visualization, evaluation, etc.).
The Fourth International Conference on Knowledge
Discovery and Data Mining -- KDD-98
Sponsored by the
American Association for Artificial Intelligence
in Cooperation with
IEEE Technical Committee on Data Engineering
New York City, New York, USA
Conference Dates: August 27-31, 1998
Exhibition Dates: August 28-29, 1998
Collocated with the
Conference on Very Large Databases (VLDB-98)
The Fourth International Conference on Knowledge Discovery and Data
Mining (KDD-98) is the premiere event for the data mining community,
bringing together researchers, practitioners and application
developers from different KDD related fields such as machine learning,
statistics, databases, data visualization, database marketing and
finance to share ideas/experiences, and to explore new concepts,
applications, tools and techniques. KDD-98 will follow the success of
previous KDD conferences and will feature technical sessions,
tutorials, panels, workshops and exhibits. We invite participants
from universities, industry and government. For more information about
the conference, please visit URL: http://www-aig.jpl.nasa.gov/kdd98.
The KDD-98 exhibits program will also follow the success of the
exhibits and demonstration sessions in previous KDD conferences,
featuring demonstrations by the leading vendors of knowledge
discovery and data mining products and services, knowledge discovery
applications and research prototypes. Unlike the previous exhibits,
KDD-98 will:
o Run the exhibits/demos in parallel with the conference so that
schedules do not interfere with each other.
o Make the exhibits/demos separately accessible from the conference
for a nominal fee, less than the conference fee.
o Separate the poster sessions from the exhibits/demos to
differentiate the academic work from the commercial companies.
o Keep the exhibits/demos area open for 1.5 days: 1/2 day on August
28th (Friday) and a full day on August 29th (Saturday).
o Invite the leading consultants providing services in the area of
knowledge discovery and data mining.
o Feature presentations by leading guest speakers in the area of
knowledge discovery and data mining.
o Advertise the exhibits/demos on the internet (in related newsgroups
and electronic journals) and in leading professional journals and
magazines.
All commercial knowledge discovery and data mining tool vendors,
consultants providing related services, academics with research
prototypes, publishers and corporations with significant applications
are welcome to exhibit at KDD-98.
+--------------------------------------------------------------------+
| Important Dates |
+--------------------------------------------------------------------+
The conference will be held in New York City, in midtown Manhattan, at
the New York Marriott Marquis Hotel between August 27-31, 1998. For
more information about the conference, please see www-aig.jpl.nasa.gov/kdd98
The exhibits/demos area will be open during the following dates/hours:
August 28, 1998: 12:00-6:00pm
August 29, 1998: 10:00-6:00pm.
The registration deadline for the commercial exhibits is:
May 1, 1998.
The registration deadline for research prototype demonstrations is:
The exhibitor fee for KDD-98 will be $500. Exhibitors will be
provided with a 6 ft. table top. In this space, exhibitors will be
allowed to distribute product/service/company literature, display
product/service demonstrations and set up signage. Exhibitors are
responsible for bringing all hardware and software required for their
demonstrations (We can provide projection equipment. Although we don't
recommend it, we can also rent hardware, if absolutely needed.)
If you would like to exhibit at KDD-98, please contact AAAI through
email at:
with the subject line 'KDD-98 Exhibits.' Please send your email before
May 1, 1998 and include the name of your product(s) and/or service(s),
and a 200 word (maximum) description of your product(s) and/or
service(s).
You may also fax or mail this information before May 1, 1998 to:
AAAI
KDD-98 Exhibits
445 Burgess Drive
Menlo Park, CA 94025 USA.
Fax: (650) 321-4457.
Your description will be published in the conference program. Please
include your email ID and complete mailing address so that we can (add
you to our mailing list to) send a complete exhibitor materials
package.
+--------------------------------------------------------------------+
| Research Prototype Demonstrations |
+--------------------------------------------------------------------+
We are also soliciting demonstrations of research prototypes at
KDD-98. We have a limited budget for providing hardware for research
demonstrations. This year we will give priority to demonstrations in
conjunction with accepted papers at KDD-98. Within budget and space
constraints we will make every effort to accommodate as many
demonstrations as possible. If you would like your demonstration to
be considered for KDD-98 please provide the following information by
March 17, 1998 to Ismail Parsa either through email (iparsa@epsilon.com),
fax (781) 272-8604 or mail to:
Ismail Parsa
Epsilon
50 Cambridge Street
Burlington MA 01803 USA.
o Name of Demonstration:
o Title of Paper:
(If this demonstration is in conjunction with a paper/poster)
o Name of Primary Contact:
o E-mail ID of Primary Contact:
o Telephone Number of Primary Contact:
o Development Team:
o Affiliations of Development Team Members:
o Description of Demonstration:
(A short description of approx. 200 words maximum)
o What is unique about your system or application?
(No more than 50 words)
o Status:
() Research prototype
() Commercially available product
() Fielded application
o Will you bring your own hardware?: ()Yes ()No
o If no, please specify
o Hardware requirements:
(Please state any special memory or disk requirements)
o Operating system:
(Please state specific version number)
o WAN Connection Required: ()Yes ()No
(If Yes, please state any special modem requirements)
o Any other requirements:
Please include your email ID and complete mailing address so that we
can add you to our mailing list to send materials as soon as they
become available.
We welcome donations to the conference to specific non-technical
events or to provide give-aways to the attendees. Under some
circumstances, corporate logos can be placed on sponsored items.
General donations are recognized in the following ways:
o Listing of company name
Co-sponsor of KDD-98 for $10,000 or more
'With support from...' for donations under $10,000.
o Signage onsite.
o Brochure and program acknowledgments.
o Listing in the AI Magazine masthead as one AAAI's corporate sponsors.
o One standard exhibit booth space for donations over $2,000.
o One complimentary registration to KDD-98, to be assigned by sponsor.
We also welcome undesignated donations so that they can be used where
the organizers see the most need.
The number of attendees has risen by over 100 people each year. Given
this, we expect about 600-800 people at KDD-98.
KDD-96
Number of Attendees: 457
Affiliations: Industry 65%
Academics 35%
KDD-97
Number of Attendees: 577 (excluding exhibitors and
workshop-only participants)
Affiliations: Research Scientist 21%
Univ/Coll Educator 13%
Student 11%
Management 10%
Programmer/Analyst 9%
Consultant 9%
Project Leader 7%
Engineer 6%
Staff Scientist 5%
Systems Analyst 2%
Administrator <1%
Other 6%
Number of Exhibitors: 17
Number of Research
Demonstrations: 9
+--------------------------------------------------------------------+
| KDD-98 Conference Site |
+--------------------------------------------------------------------+
The conference will be held in New York City, in midtown Manhattan, at
the New York Marriott Marquis Hotel. New York City is the
international mecca (of everything) from high-powered businesses,
including financial, advertising, publishing and media worlds, to the
grand stage of culture and the allure of the American fashion.
The New York metropolitan area houses 18 million people and spans 3
states -- New York, New Jersey and Connecticut. Other major
metropolitan areas such as Philadelphia, PA and Wilmington, DE are an
hour away from the conference location.
Enthusiasm for exploiting the association between Barbie and candy buying
habits may be overrated - instead of bringing Barbies and candies closer to
each other, we may need to put them as far as possible.
Let me explain why.
As Tom Dinsmore dinsmore@think.com
have pointed out, the association is
most probably caused by some unmeasured, latent, variable. For example,
Barbie dolls may already be on a shelf in the middle of the candy
department. Or, each doll is sold with a discount coupon for the candies.
Then the correct conclusion is
1) 'Barbie-buyers are eager to buy the merchandise that is in their way', or
2) 'they are easily influenced by the advertisement'.
This is good - now, instead of feeding them the cheap candies, you may
start putting high-profit items in their way - or even start a
direct-marketing campaign.
p.s. using information about time of the purchase might help to find out
whether dolls and candies are always bought together ( then, go to
conclusion 1) or not necessarily (then, conclusion 2).
Starting early in 1999, Springer-Verlag will publish a new quarterly
journal called 'Knowledge and Information Systems: An International
Journal.' This journal has grown out of increasing demands of such a
rapidly growing field in Asia, Europe, and North America.
Please find attached the instructions for authors and the aims and
scope of the journal. We strongly encourage electronic submissions to
expedite processing, and Springer-Verlag will offer the journal in
both electronic as well as print form. The editors will emphasize
minimal delay in processing and publication, and plan to review papers
quickly and advise authors of their paper status with a target
turnaround time of 3 months from submission (4 to 6 weeks for short
papers).
Best regards,
Benjamin W. Wah Xindong Wu Ian Shelley
Honorary Editor-in-Chief Executive Editor Springer-Verlag
University of Illinois, Monash University
Urbana-Champaign
Knowledge and Information Systems: An International Journal
===========================================================
Knowledge and Information Systems (KAIS) provides an international
forum for researchers and professionals to share their knowledge and
report new advances on all topics related to knowledge systems and
advanced information systems. This quarterly peer-reviewed journal
publishes state-of-the-art research reports on emerging topics in
KAIS, reviews of important techniques in related areas, and
application papers of interest to a general readership.
The journal focuses on knowledge systems and advanced information
systems, including their theoretical foundations, infrastructure and
enabling technologies. We solicit submissions of original research,
and experience and vision papers that address this theme. Suggested
topics include, but are not limited to, the following areas:
- Knowledge and Information Processing: Theory, Techniques and Systems
- Underlying Computational Techniques
- Platforms
- Application to Specific Problem Domains
We publish critical review papers in each issue of the journal to
discuss the state of the art in particular areas, as well as
state-of-the-art research reports. Accepted papers are grouped for
publication so that individual issues focus on a small number of theme
areas. In addition to archival papers, the journal also publishes
significant on-going research in the form of Short Papers (limited to
3000 words). We conduct reviews in a timely fashion and inform authors
of decisions with a target turnaround time of 3 months (4 to 6 weeks
for short papers).
For more information, including submission instructions see the journal web
site above.
<> Previous5NextTop
Date: Thu, 26 Feb 1998 16:09:24 +0800
From: beat wuthrich beat@cs.ust.hk
Subject: Daily stock forecast from textual Web data
this site gives info about a real-time system predicting the world's
major stock markets
on a daily bases; the system's prediction are displayed every morning
7:45 am HK time.
B. Wuthrich
Ass Prof, HKUST
Clear Water Bay
Hong Kong
[P.S. this forecast is provided without any warranty to how accurate it
might be]
Previous6NextTop
From: 'Gerardo Capiel' gcapiel@pacbell.net
Subject: San Francisco: Internet Start-Up job
Date: Wed, 11 Feb 1998 11:48:20 -0800
INTERNET START-UP LOOKING FOR ANALYSTS
Digital Impact, Inc. a San Francisco venture-backed start-up is looking for
statisticians fluent in direct marketing, SAS, and other statistical tools.
Digital Impact provides direct marketing/database marketing services to
Internet marketers who are selling branded consumer products on the web. The
company recently received venture funding and is looking to build a world-class
analytics group to work alongside its talented web development team.
Digital Impact and its prestigious clients are very excited about the
potential applications of advanced analytics to the web - a medium which
justifies new approaches that are not economically practical with
traditional print and postage.
The company invites top data miners/statisticians who can think
out-of-the-box in the
direct marketing/database marketing domain to apply. In addition to
competitive salaries, we offer stock options and tremendous responsibility.
We have both director level and project analyst positions open.
Gerardo Capiel
Chief Technology Officer
Digital Impact, Inc.
944 Noe St.
San Francisco, CA 94114
415-541-8482 gcapiel@digital-impact.com
Researcher/Developer of Data Mining/KDD Technologies
Provide technical and scientific expertise in core technologies for Data
Mining and Knowledge Discovery: Machine Learning, Artificial
Intelligence, Multivariate Statistics and High Performance Computing.
Design, spec and develop state-of-the-art Machine Learning/Statistical
modules for scalable Data Mining engine and applications (C++). Evaluate
the advantages or disadvantages of new algorithms from a technical and
strategic perspective. Develop new methods to understand and improve the
generalization capabilities of general predictors. Create business
application-oriented Data Mining frameworks.
The requirements for this position are a Ph.D. in Computer or Physical
Sciences, at least two or three years of experience designing and
developing statistical or machine learning algorithms and an outstanding
track record in the form of publications or completed projects.
Familiarity with object oriented and state-of-the-art software
development techniques is also required. Experience with business Data
Mining problems, UNIX/NT and High Performance Computing is a plus.
THE FIFTEENTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING
July 24-26, 1998
Madison, Wisconsin, USA
The Fifteenth International Conference on Machine Learning (ICML-98)
will be held at the University of Wisconsin, Madison from
July 24 to July 26, 1998. ICML-98 will be collocated with the Eleventh
Annual Conference on Computational Learning Theory (COLT-98) and the
Fourteenth Annual Conference on Uncertainty in Artificial Intelligence
(UAI-98). Seven additional conferences, including the Fifteenth National
Conference on Artificial Intelligence (AAAI-98), will also be held in
Madison (see http://www.cs.wisc.edu/icml98/
for a complete list).
Submissions are invited that describe empirical, theoretical, and
cognitive-modeling research in all areas of machine learning.
Submissions that present algorithms for novel learning tasks,
interdisciplinary research involving machine learning, or innovative
applications of machine learning techniques to challenging, real-world
problems are especially encouraged.
***** The deadline for submissions is MARCH 2, 1998. ******
(An electronic version of the title page is due February 27, 1998.)
PLEASE NOTE THAT THESE ARE FIRM DEADLINES.
See http://www.cs.wisc.edu/icml98/callForPapers.html
for submission details.
(There also will be three joint ICML/AAAI workshops.
The submission deadline for these WORKSHOPS is MARCH 11, 1998.
See http://www.cs.wisc.edu/icml98/
for further details.)
[My apologies if you receive multiple copies of this announcement.]
Call for Presentations
PAKDD Workshop on Parallel and Distributed Data Mining
PDDM'98
Melbourne Convention Centre, Melbourne, Australia
15th April 1998
Data mining is the automatic discovery of patterns, changes,
associations and anomalies in large data sets. Data mining is
emerging as a key enabling technology for a variety of scientific,
engineering, medical and business applications. This workshop for
focus on three key issues:
1. Scaling data mining algorithms, applications and systems to massive data sets.
2. Developing data mining algorithms, applications and systems for
mining distributed data.
3. Integrating data mining with other systems and applications.
This workshop aims to bring together researchers working on all
aspects of parallel and distributed data mining during the PAKDD 98
conference. The workshop is scheduled for one day and includes
presentations and discussions.
To guarantee consideration, abstracts must be received by March 15,
1998. Authors will be notified of acceptance by March 16, 1998. The
final versions of the papers will be submitted after the workshop for
publication.
<> Previous10NextTop
Date: Thu, 12 Feb 1998 10:55:09 +0100
From: Yves.Kodratoff@lri.fr
(Yves Kodratoff)
Subject: Meeting on Knowledge Discovery and Data Mining
ESIEA Group`s Research Center organizes a
Meeting on Knowledge Discovery and Data Mining
Paris March 18th 1998
Hotel PARIS HILTON
18, avenue de Suffren
75015 Paris
The program includes talks and demos by
Loe Carbonara (British Telecom)
Anne-Marie Kempf (ESIEA)
Yves Kodratoff (CNRS)
Ron Kohavi (Silicon Graphics)
Thierry Van de Merckt (CSC)
Djamel Zighed (Univ. Lyon 2)
NSF Knowledge and Distributed Intelligence (KDI) meeting,
Minneapolis, MN , March 7, 1998
New NSF Initiative: KD Researchers Should Apply. Deadlines Quickly Approaching
The National Science Foundation has announced a new initiative entitled
Knowledge and Distributed Intelligence (KDI). KDI aims to bring together
expertise from all areas of science, to focus on a variety of questions in
communications and networking, understanding learning and intelligence, and
computation. Letters of intent are due April 1 and full proposals are due May 8.
An informational workshop is being planned Saturday, March 7 at the
Institute for Mathematics and its Applications (IMA) in Minneapolis,
MN; the tentative schedule is below. Other workshops will be held
Friday, February 27 at Mathematical Sciences Research Institute (MSRI)
in Berkeley, CA; and Monday, March 9 at the National Institute of
Statistical Sciences (NISS) at Research Triangle Park, NC. See http://www.ima.umn.edu/kdi.html
for details and registration forms.
NSF's KDI budget is expected to be about $62 million for fiscal year 1998, and
grants are expected to range from about $100,000 up to $1,000,000 per year.
For detailed information and continuing developments, consult the web
site http://www.nsf.gov/kdi.
General questions about KDI may be sent to
the e-mail address kdi@nsf.gov.
Specific topical questions in one of the
three KDI focus areas may be sent to: kn@nsf.gov
(for Knowledge
Networking), lis@nsf.gov
(for Learning and Intelligent Systems), and to ncc@nsf.gov
(for New Computational Challenges).
Previous12NextTop
From: pakdd98-announce@deakin.edu.au
Date: Fri, 20 Feb 1998 14:42:37 +1100
Subject: PAKDD-98: Advance Program and CFP
********************
* P A K D D ' 98 *
********************
2nd Pacific-Asia Conference on Knowledge Discovery and Data Mining
Melbourne, Australia, April 15-17, 1998
C A L L F O R P A R T I C I P A T I O N
Sponsored by:
MAIC: Monash Artificial Intelligence Consortium
School of Computer Science and Software Engineering, Monash University
ACSys: Cooperative Research Center for Advanced Computational System
Invited Speakers:
Jiawei Han (ACSys Keynote Speaker, Simon Fraser University, Canada)
Chris Wallace (Monash University, Australia)
Bhavani Thuraisingham (MITRE Corporation, USA)
Conference Chairs:
Ross Quinlan (RuleQuest Research Pty Ltd)
Bala Srinivasan (Monash University)
Program Chairs:
Xindong Wu (Monash University)
Ramamohanarao Kotagiri (Melbourne University)
INTRODUCTION
============
The Second Pacific-Asia Conference on Knowledge Discovery and Data
Mining (PAKDD-98) provides an international forum for the sharing of
original research results and practical development experiences among
researchers and application developers from different KDD related
areas such as machine learning, databases, statistics, knowledge
acquisition, data visualization, software re-engineering, and
knowledge-based systems. It follows the success of PAKDD-97 held in
Singapore in 1997 by bringing together participants from universities,
industry and government.
The conference program consists of 2 tutorials, 3 invited talks, one
panel discussion, one pre-conference workshop, and a number of
technical sessions for refereed paper presentations. The topic of the
panel discussion is `To What Extent Can Data Mining Be
Proceduralised?', and the theme of the workshop is `Parallel and
Distributed Data Mining'. The 2 tutorials are `Data Mining: An
Overview from Database Perspective' and `Applications of Minimum
Message Length in Data Analysis'.
ANALYSIS OF ENVIRONMENTAL DATA WITH MACHINE LEARNING METHODS
17.-20. March 1998, Ljubljana, Slovenia
Organized by Jozef Stefan Institute, Ljubljana, in cooperation with
University of Ljubljana and European Graduate School of Hydraulics
Area and goals of the seminar
The seminar will give an introduction to selected machine learning methods
as well as illustrative case studies of using these methods to analyse
environmental data, such as modeling algal growth in lakes and lagoons,
analysing the influence of physical and chemical parameters on selected
bioindicator organisms, and predicting the biodegradability of chemical
compounds. The participants will learn to use selected machine learning
tools and will have the opportunity for practical work with these tools on
real environmental data. The machine learning methods and tools introduced are
applicable to data analysis problems from different areas.
Who should attend the seminar
The seminar is intended for researchers and other professionals in the areas
of biology, chemistry, environmental science, and other areas related to
ecology and environmental management, whose work requires the analysis of
environmental data or modeling ecological processes.
* Introduction to machine learning
o Bayesian classification
o Neural networks
o Instance-based learning (nearest neighbor classification)
o Learning decision (classification) and regression trees
o Learning classification rules
o Machine discovery of equations
o Inductive logic programming
* An overview of environmental applications of machine learning
o Analysis of the influence of environmental factors on respiratory
diseases
o Analysis of the influence of soil habitat features on the
abundance of Collembola
o Modeling phytoplankton growth
o Modeling interactions among red deer population, meteorological
parameters and new forest growth
* Case studies of using machine learning to analyse ecological data
o Analysis of water quality data (Slovenian and English rivers)
o Modeling algal growth in the Lagoon of Venice
o Predicting biodegradability of chemical compounds
o Runoff prediction from rainfall and past runoff
* Demonstrations/practical work with machine learning software packages
on real ecological data and individual consultations with lecturers