Mining negative rules using GRD

20
2006/10/25 1 Mining negative rules using GRD D. R. Thiruvady and G. I. Webb PAKDD 2004

description

Mining negative rules using GRD. D. R. Thiruvady and G. I. Webb PAKDD 2004. Outline. Introduction OPUS GRD Conclusion. Introduction. Association rule A ==> B (A is antecedent ,B is consequent) Negative Rules Either antecedent or consequent or both are negated. - PowerPoint PPT Presentation

Transcript of Mining negative rules using GRD

Page 1: Mining negative rules using GRD

2006/10/25 1

Mining negative rules using GRD

D. R. Thiruvady and G. I. Webb

PAKDD 2004

Page 2: Mining negative rules using GRD

2006/10/25 2

Outline

• Introduction

• OPUS

• GRD

• Conclusion

Page 3: Mining negative rules using GRD

2006/10/25 3

Introduction

• Association rule – A ==> B (A is antecedent ,B is consequent)

• Negative Rules– Either antecedent or consequent or both are negated

A B A B

A B

Page 4: Mining negative rules using GRD

2006/10/25 4

Optimized Pruning for Unordered Search (OPUS)

Page 5: Mining negative rules using GRD

2006/10/25 5

Generate Rule Discovery (GRD)

• Extends OPUS by remove the requirement that consequent be single variable

• K number of rules replace minimum support

Page 6: Mining negative rules using GRD

2006/10/25 6

GRD

• Four measures with respect to a rule XY

Page 7: Mining negative rules using GRD

2006/10/25 7

GRD

• Symbol

Page 8: Mining negative rules using GRD

2006/10/25 8

Properties

Page 9: Mining negative rules using GRD

2006/10/25 9

Properties

Page 10: Mining negative rules using GRD

2006/10/25 10

Properties

Page 11: Mining negative rules using GRD

2006/10/25 11

Properties

Page 12: Mining negative rules using GRD

2006/10/25 12

GRD

• Symbol– CurrentLHS: Init ψ– AvailableLHS: Init Antecedent– AvailableRHS: Init Consequent

• Function– Insolution(ac): rule ac in solution– Proven(X): pruning rules provided to the alg

orithm prove the proposition X

Page 13: Mining negative rules using GRD

2006/10/25 13

GRD algorithmPrune 1

Prune 2

Prune 3,4,5

Page 14: Mining negative rules using GRD

2006/10/25 14

GRD algorithm2Prune 6

Page 15: Mining negative rules using GRD

2006/10/25 15

Pruning

Page 16: Mining negative rules using GRD

2006/10/25 16

Pruning

Page 17: Mining negative rules using GRD

2006/10/25 17

Pruning

Page 18: Mining negative rules using GRD

2006/10/25 18

Update Constraints

Page 19: Mining negative rules using GRD

2006/10/25 19

Negative with GRD

support(A & B) support(A B) support(A & B)x x

support(A B) support(A) support(A B)

Page 20: Mining negative rules using GRD

2006/10/25 20

Conclusion

• Disadvantage– Search space too large