Critique of the dirty dozen: 12 years of KDD

Slides:



Advertisements
Similar presentations
Science Science is  The process of trying to understand the world  A way of knowing, thinking and learning  Based on observation and experimentation.
Advertisements

Scientific Process.  What is an INFERENCE? When you explain or interpret things by using past knowledge and observations.  Reasonable Inferences: Make.
An Extension of Table Lens CPSC 533 Information Visualization Course Project, Term 2, 2003 Fengdong Du.
1 On Demand Classification of Data Streams Charu C. Aggarwal Jiawei Han Philip S. Yu Proc Int. Conf. on Knowledge Discovery and Data Mining (KDD'04),
Beluga Whales Case Study Understandings About Scientific Inquiry.
ACT SCIENCE.
Warmup How is an airplane flight simulator a kind of model? What are some advantages to training pilots in a flight simulator rather than in a real.
Feels Like a ” Real” Patient Interaction
Research, innovation, and evaluation, and framing inquiry
Feeling Welcome – your experience
Chapter 1 The Science of Biology.
Chapter 1 Introduction: Themes in the Study of Life
C. Titus Is it possible to get a scientific field to collaborate on data integration? Some thoughts from an experience.
Predictive Customer Engagement
The Goal of Biblical Marriage
AF1: Thinking Scientifically
Words to Know Hypothesis (prediction)- Testable prediction based on observations. Usually an if/then/because statement. Inference- a conclusion reached.
Introduction to Data Mining
WHAT IS THE NATURE OF SCIENCE?
The Scientific Process or Method
Scientific Method Quiz
Chapter 1 – The Science of Biology
Understand Decision Making
Channel Surfing Online
Investigation How to write it up.
How to take notes… The Crainum Way!
What Is Anthropology and Why Should I Care?
The Nature of Science What is Science..?.
Lesson Overview 1.2 Science in Context.
Scientific Method.
Scientific Method.
Levels of Scientific Knowledge
The process of thinking scientifically
Boosting Agent Productivity and Contact Centre Efficiency
The Scientific Method.
1-1 What is Science? What Science Is and Is Not
Scientific Method.
1.2 Science in Context----Outline
Qualitative Observation
Learning Analytics: Process & Theory
Scientific inquiry: a method
The process of thinking scientifically
The Scientific Method.
Life Science Chapter 1 Review
Organizing Data How do scientists organize data?.
THE NATURE OF SCIENCE.
Web Mining Department of Computer Science and Engg.
What Is Science?.
Psychology 101 What is psychology?.
Science is... An organized way of using evidence to learn about the natural world Based on observations.
The Scientific Method.
Science is... An organized way of using evidence to learn about the natural world Based on observations.
Defining the Grid Fabrizio Gagliardi EMEA Director Technical Computing
Evolution Part Two.
Feeling Welcome – your experience
ARMA Spring Chapter Recruitment Campaign
STRUCTURE Introduction of the general research topic Statement of specific research questions Critical review of previous literature Theoretical argument.
Carl Rogers Person-Centered Humanistic & Existential
How to get full CX value from your digital support channels
Process of the Scientific Method
The Nature of Science.
Theory, Education, & Learning
Ch. 1 The Nature of Science
Valence and Core Electrons
Areas of Program Focus: Developing Great Agents
Scientific method.
Why now? New requirement for all RACs in the next Request for Applications (RFA) Improve communications among all participants Increased need to identify.
P Science in Context.
Experiments A guide to managing experiment work in Construction Studies
The Scientific Method The Purpose/Question Observation/Research
Presentation transcript:

Critique of the dirty dozen: 12 years of KDD Daryl Pregibon AT&T Shannon Laboratory daryl@research.att.com KDD2001 San Francisco, CA

Summary There remains tremendous opportunity for data mining on the horizon To take full advantage of these opportunities some changes are necessary

The KDD Community (who we are) AI DB Stats/ML

KDD Activities (what we do) Theory Methods Applications

We do too much of e-verything e-commerce e-business e-tailing e-this e-that e-nough already!

We focus too much on predictive accuracy Data mining should be about story telling i.e., understanding and interpretability Why can’t we strive to have both - highly accurate predictions and interpretability?

We don’t do enough of…. Foundations/fundamentals Is there a Shannon-like theory for capacity in a data mining channel? We have many ways to quantify the amount of data in a DB (#rows/ #tables/ #bytes) so why can’t we do the same for the amount of information in a DB?

Scientific applications Genomic DBs change the dynamic --- will the KDD community respond? Automation We already have more data than anyone could ever look at --- where are the data mining agents? The classibots? The regressibots? Knowledge Discovery in Data as a process More than just tactics! Education How do we train the data mining generation?