KDD Nugget 94:23, e-mailed 94-12-27 Contents: * GPS, ComputerWorld on "AI Determines Customer Preference" * GPS, KDD Nuggets in 1995 Directory of Electronic Journals * D. Druker, Siftware: Essbase Multi-Dimensional OLAP Server * M. Holsheimer, Siftware: Data Surveyor * M. Manago, CFP: IJCAI CBR Workshop * B. Julien, CFP: IJCAI workshop on Machine Learning in Engineering * M. Scmill, CFP: AI journal special issue on Empirical AI **************************************************************************** * for those of you without WWW access: * -- I have updated FTP site on 94-12-27, so it now contains everything * in WWW site, including archives of Nuggets and Siftware. GPS **************************************************************************** The KDD Nuggets is a moderated mailing list for news and information relevant to Knowledge Discovery in Databases (KDD), also known as Data(base) Mining, knowledge extraction, etc. Relevant items include workshop and conference announcements, tool announcements and reviews, summaries of publications, information requests, interesting ideas, clever opinions, etc. Nuggets frequency is approximately bi-weekly, depending on the quantity and urgency of submissions. Back issues of Nuggets, a catalog of database mining tools, useful references, FAQ, and other KDD-related information are now available at Knowledge Discovery Mine, URL http://info.gte.com/~kdd/ or by anonymous ftp to ftp.gte.com, cd /pub/kdd, get README E-mail add/delete requests to kdd-request@gte.com E-mail contributions to kdd@gte.com -- Gregory Piatetsky-Shapiro (moderator) ********************* Official disclaimer *********************************** * All opinions expressed herein are those of the writers (or the moderator) * * and not necessarily of their respective employers (or GTE Laboratories) * ***************************************************************************** ~~~~~~~~~~~~ Quotable Quote ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ "Reflect upon your present blessings, of which every man has plenty; not on your past misfortunes, of which all men have some." - Charles Dickens ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -------------------------------------------- From: gps@gte.com (Gregory Piatetsky-Shapiro) Subject: ComputerWorld on "AI Determines Customer Preference" Date: Tue, 27 Dec 1994 An article by Julia King in ComputerWorld, Nov 14, 1994, page 120, entitled "AI Determines Customer Preference", describes work of a Philadelphia-based company named Pattern Discovery Inc., on analysis of customer surveys. Founded by Steven Hokanson, former manager of an AI program at Boeing, the firm employs analysis methods based on AI and fuzzy logic. The idea is to find relationships between different variables, pinpointing those that have a "halo" effect on customer's overall perceptions. In the case of a large fast-food company, restroom cleanliness was found to have such an effect on customer's overall perception. For Public Service Gas and Electric in Newark, NJ, billing accuracy was directly related to how customers rated the reliability of electric service. Other Pattern Discovery customers include Celtic Life Insurance in Chicago, Roadway Express in Akron, Ohio, and Volvo of North America in Rockleigh, N.J. So far Pattern Discovery analyzed customer returns for about 25 Fortune 1000 clients. -------------------------------------------- From: gps@gte.com (Gregory Piatetsky-Shapiro) Subject: KDD Nuggets in Directory of Electronic Journals Date: Tue, 27 Dec 1994 KDD Nuggets will be included in 1995 Directory of Electronic Journals, Newsletters and Academic Discussion Lists, published by the Association of Research Libraries. The directory has a wide readership in both its print and electronic versions and is recognized as the standard reference work for e-serials. An abridged version of last year's directory is available on the ARL gopher. The URL is gopher://arl.cni.org:70/11/scomm/edir/edir94 -------------------------------------------- Date: Sat, 3 Dec 1994 13:33:47 -0800 To: kdd@gte.com From: ddruker@netcom.com (Daniel Druker) Subject: Siftware Submission Here's a submission for your Siftware list of software. You might want to create a new category called Dimensional Analysis, and put this tool and Cross Target in it. *Name: Essbase Multi-Dimensional OLAP Server *Description: Essbase is a high-performance multi-dimensional analytical engine for OLAP (On-Line Analytical Processing.) It allows very rapid analysis of extremely large data sets. Essbase is fully client/server 32-bit, multithreaded, SMP enabled. Essbase supports an unlimited number of dimensions, and an unlimited number of members per dimension. Essbase provides an Open API for client access, and works with a number of popular front-end tools. *Discovery methods: N/A: Essbase acts as a server to a range of analytical front-end tools. Essbase provides vastly superior performance as compared with a typical relational database. *Comments: See also the comp.databases.olap usenet newsgroup for a discussion of On-Line Analytical Processing (OLAP), a relatively new category of analytical tools defined by Dr. EF Codd. *Source: ddruker@arborsoft.com *Platform(s): Windows, Mac, OS2, NT, Unix *Contact: Arbor Software Corporation 1325 Chesapeake Terrace Sunnyvale, CA, 94089 1-800-858-1666 ddruker@arborsoft.com *Status: commercial software product *Updated by: Dan Druker ddruker@netcom.com 12/2/94 -------------------------------------------- To: gps0%eureka@gte.com (Gregory Piatetsky-Shapiro) Subject: Data Surveyor Date: Tue, 20 Dec 1994 18:10:56 +0100 From: Marcel Holsheimer Dear Gregory, Could you add the following information to the siftware list: *Name: Data Surveyor *Description: Data Surveyor is a data mining tool for the discovery of strategic relevant information from large databases. *Discovery methods: Induction of classification rules *Source: information by author *Comment: uses a separate front and back-end. The front end directs the mining process, where the back-end is a fast, parallel, main memory database server. and performs all massive data handling. *Platform(s): Back-end currently runs on (parallel) Unix systems, front-end runs on Unix workstations and MS-Windows. *Contact: Marcel Holsheimer at CWI, The Netherlands. E-mail: marcel@cwi.nl, tel. +31-20-592 4134, fax +31-20-592 4199, P.O. Box 94079, 1090 GB Amsterdam, The Netherlands. *Status: product *Updated by: Marcel Holsheimer on 1994-12-20 Could you also announce the Data Surveyor produkt information on the kdd mailing list? Thank you. Best regards, Marcel. -------------------------------------------- Return-Path: Date: 12 Dec 94 18:54 GMT From: ACKNOWLEDGE@applelink.apple.com (ACKNOWLEDGE, PARIS,FR,IDP) Subject: IJCAI CBR workshop To: KDD@gte.com PRELIMINARY CALL FOR PARTICIPATION IJCAI workshop on practical applications of CBR In late august in Montreal/Canada, I (Michel Manago, President AcknoSoft, France), Stefan Wess (Inference Germany/University of Kaiserslautern) and Rakph Barletta (President of Case-Data Solutions USA, former leader of the Remind project when he was working at CSI), will organise an IJCAI workshop entitled "Practical Applications of Case-Based Reasoning (CBR)". The goal of the workshop is to discuss all aspects of the development and the lifecycle (validation, scaling up and maintenance) of real world CBR applications and to begin to reach a consensus about to the most important issues in building and maintaining CBR systems. We will also discuss what are the best techniques, from a practical standpoint, for addressing those issues. Topics of interest include : Foundational issues and core problems in CBR Description of outstanding CBR applications CBR tools and techniques for dealing with real life applications Integration of CBR technology in existing information systems Organizational issues relating to putting CBR technology to use Use of Background Knowledge in CBR systems Case modelling, case acquisition, case indexing Assessing similarities between cases Generalization of cases/forgetting old case that are no longer relevant Adaptation techniques for real world problems Future research topics in CBR to handle real life problems The list of topics is not intended to be exhaustive. Rather than have participants prepare papers and presentations prior to the workshop, we intend to have the participants break into small groups of 4 or 5 in the morning of the workshop to discuss various predefined issues (that will be further refined via exchanges of e-mails prior to the workshop) and come with a consensus of opinion whenever possible, or a list of topics that require further investigations, for presentation to the larger workshop group in the afternoon. We will also encourage demonstration of CBR applications during the workshop. The following are examples of some of the issues we could have the breakout groups discuss : - Is case adaptation important in real world applications? If not, why? If so, how is it done to produce results that are satisfactory to the end user? Can we come up with a classification of applications where case adaptation is essential? - How does the application developer determines what kinds of cases to go looking for? Can we come up with a case acquisition methodology? - Methods for forgetting or aggregating stuctured cases into abstract cases for use in CBR tools - What interface approaches do users find most effective for interacting with the case library to do problem solving? - Is a separate case library and event database acceptable/preferable for delivering and maintaining the application? Attendance will not be limited to industry. CBR practitionners working in academic institutions who have been developping real life CBR systems are encouraged to attend this workshop as well. The fee for the workshop is modest (about 50$). Participants to the workshop MUST BE REGISTERED TO THE IJCAI CONFERENCE AS WELL. If you are interested in participating please send as soon as possible a one page abstract that best describe why you consider yourself a CBR practitionner with any additional elements that demonstrates that you have indeed been involved in building a REAL LIFE CBR application that has, preferably, been fielded to : ACKNOSOFT IJCAI CBR Workshop 58 rue du Dessous des Berges 75013 PARIS tel: (331) 44 24 88 00 Fax : (331) 44 24 88 66 and a written statement that you will participate to this IJCAI workshop and to the IJCAI conference if you are selected by the Programme Committee (that is itself being selected at the present time...). -------------------------------------------- From julien@magnum.crim.ca Tue Dec 20 11:35:07 1994 Return-Path: Date: Wed, 14 Dec 94 13:46:06 EST From: julien@magnum.crim.ca (Benoit Julien) To: kdd@gte.com Subject: Machine Learning in Engineering - Call for Participation Cc: julien@crim.ca For posting: =========================================================================== CALL FOR PARTICIPATION *** Workshop on Machine Learning in Engineering *** International Joint Conference on Artificial Intelligence 1995 IJCAI-95 Montreal, Quebec, Canada August 19-25, 1995 =========================================================================== WORKSHOP OBJECTIVES The last ten years have witness a significant increase in the development of knowledge-based systems for engineering applications. As in other domains, the success of knowledge-based approaches in engineering depends critically on the quality of the knowledge acquisition process. Computer-aided engineering system developers in the early nineties quickly recognized the potentials offered by emerging machine learning techniques. As machine learning moves from "toy" problems to "real" engineering applications, a concerted R&D effort becomes essential to identify and overcome critical engineering knowledge acquisition bottlenecks. In that perspective, this workshop will bring together researchers applying or developing machine learning techniques for various engineering disciplines in order to establish important commonalities and differences in engineering learning problems. This forum will permit the definition of basic engineering learning tasks and their relationships with appropriate machine learning strategies. By presenting the state-of-the-art in machine learning applications to engineering, this event should also bridge many gaps between machine learning theory and engineering practice. TOPICS OF INTEREST All researchers and practitioners actively applying or developing machine learning techniques to engineering problems are encouraged to submit papers for this workshop. Topics of interest include, but are not limited to, the following: * Case studies Case studies of application of machine learning in engineering, with analysis of successes and failures. Examples of application topics: - Knowledge mining of engineering databases; - Engineering learning apprentice systems; - Semi-automated engineering knowledge acquisition; - Constructive induction in engineering; - Engineering knowledge discovery systems; - Engineering model acquisition and refinement. * Comparative studies Comparative studies of machine learning techniques solving similar engineering learning tasks; * Overviews Overviews of the state-of-the-art of machine learning in engineering; * Position papers on key issues Position papers discussing and proposing methodologies for solving important engineering learning issues. Examples of key issues: - Prior knowledge in engineering learning problems; - Tracking engineering concept drifts (dynamic knowledge); - Mapping of generic engineering tasks with learning techniques; - Multistrategy learning for engineering problems; - Machine learning for engineering data analysis; - Learning from very small or very large training sets; - Learning from noisy training sets; - Integration of machine learning and knowledge acquisition. Papers describing strictly manual knowledge acquisition and maintenance case studies are discouraged. This workshop does not cover applications of subsymbolic learning techniques such a neural networks and genetic algorithms. SUBMISSIONS All papers submitted should not exceeed 15 pages. The organizers intend to publish a selection of the accepted papers as a book or a special issue of a journal. The authors should take this into account while preparing their papers. In order to encourage the submission of work in progress reports, 5 pages extended abstracts will also be accepted for submission. However, the accepted extended abstracts will not be considered for later publication. Copies of the workshop proceedings containing all accepted papers and extended abstracts will be prepared and made available by IJCAI at the workshop. Each paper and extended abstract should provide a clear description of the engineering task and the learning problem so that other participants not familiar with the application can easily understands the key characteristics and objective of the research. The papers should also define all technical terms and make explicit the research methodology and the underlying characteristics and assumptions of the learning problem(s) and technique(s). The authors should also discuss important future issues as well as implications and possible extensions of their work to other engineering domains. Each submitted paper and extended abstract will be reviewed by at least three members of an international program committee and will be judged on significance, originality, and clarity. Papers submitted simultaneously to other conferences or journals must state so on the title page. Those who would like to attend the workshop without giving a presentation should send a 1 page description of relevant research interests with a short list of selected publications. Please send general inquiries to julien@crim.ca. DEADLINES Four (4) hard copies of the papers or extended abstracts must be received by the workshop organiser by February 17, 1995. Alternatively, electronic submissions in postscript are encouraged. FAX submissions are not acceptable. Notification of acceptance or rejection will be sent to the first (or designated) author with the reviewers comments by March 24, 1995. Final camera-ready papers and extended abstracts should arrive by April 21, 1995. This one-day workshop will be held between Saturday 19 August and Monday 21 August 1995 inclusive. PAPER FORMAT Submissions must be clearly legible, with good quality print. Papers and extended abstracts are respectively limited to a total of 15 and 5 pages including title page, bibliography, tables and figures. Papers must be printed on 8.5 x 11 inch paper or A4 paper using 12 point type (10 characters per inch) with a 1 inch margins and no more than 40 lines per page. The title page must include the names, postal and electronic (e-mail) addresses and phone and FAX numbers of all authors together with an abstract (200 words maximum) and a list of key words. The first key words should specify the engineering domain (e.g., electrical, civil, mechanical, industrial, chemical, environmental, metalurgy, mining), the engineering generic task (e.g., classification, scheduling, control, maintenance, planning, design), and the machine learning technique(s) used (e.g., case-based learning, conceptual clustering, explanation-based learning, rule induction, inductive predicate logic). Papers without this format will not be reviewed. To save paper and postage costs please use double-sided printing or, preferably, send a postcript file via internet to the workshop organizer. WORKSHOP FORMAT The format of the workshop will be paper sessions with discussion at the end of each session. The day will be divided in four (4) thematic sessions of an hour and a half each. A commentator from the program committee will be assigned for each presentation so as to initiate and supervised the discussions. The workshop will conclude with a panel discussion. The panel discussions will be instrumental in establishing guidelines for future integrations and collaborations and a research agenda for the next five years based on the key multidisciplinary issues identified. The number of participants to the workshop is limited to 40. All workshop participants are expected to register for the main IJCAI conference and to pay an additional fee ($US 50) for the workshop. WORKSHOP CHAIRS Benoit Julien (workshop organiser) Centre de recherche informatique de Montreal (CRIM) 1801, McGill College avenue, Suite 800 Montreal (Quebec) H3A 2N4 Canada phone: 1-514-398-5862 fax: 1-514-398-1244 e-mail: julien@crim.ca Steven J. Fenves Department of Civil Engineering Carnegie Mellon University Pittsburgh, PA, 15213 United States phone: 1-412-268-2944 fax: 1-412-268-7813 e-mail: fenves@ce.cmu.edu Tomasz Arciszewski Systems Engineering Department School of Information Technology and Engineering George Mason University Fairfax, VA, 22030 United States phone: 1-703-993-1513 fax: 1-703-993-1706 e-mail: Tarcisze@gmu.edu -------------------------------------------- Return-Path: From: Matt Schmill Subject: More Info, Special Issue of AIJ on Empirical AI To: lantra-l%finhutc.bitnet@cunyvm.cuny.edu, corpora@nora.hd.uib.no, qphysics@cs.washington.edu, vision-list@teleos.com, kdd@gte.com Date: Thu, 22 Dec 1994 15:55:31 -0500 (EST) Reply-To: cohen@cs.umass.edu X-Mailer: ELM [version 2.4 PL20] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Content-Length: 480 This is to remind you that papers for the Special Issue of the AI Journal on Empirical AI, edited by Paul Cohen and Bruce Porter, are due on January 10, 1995. The Call for Papers is published at ftp://ftp.cs.umass.edu/pub/eksl/misc/cfp.txt or http://eksl-www.cs.umass.edu/cfp.html Or you can send email to cohen@cs.umass.edu. Please send three copies of your paper to: Paul Cohen Computer Science Department, LGRC University of Massachusetts Box 34610 Amherst, MA 01003-4610 --------------------------------------------