20
1 1 Chapter 1: Introduction 1.1 Introduction to SAS Enterprise Miner

Chapter 1: Introductionberka/docs/4iz450/EM_introduction.pdfSAS Enterprise Miner Analytic Strengths Predictive Modeling Pattern Discovery 20 Applied Analytics Case Studies Bank usage

Embed Size (px)

Citation preview

1 1

Chapter 1: Introduction

1.1 Introduction to SAS Enterprise Miner

2

SAS Enterprise Miner

2

3

SAS Enterprise Miner – Interface Tour

3

Menu bar and shortcut buttons

4

SAS Enterprise Miner – Interface Tour

4

Project panel

5

SAS Enterprise Miner – Interface Tour

5

Properties panel

6

SAS Enterprise Miner – Interface Tour

6

Help panel

7

SAS Enterprise Miner – Interface Tour

7

Diagram workspace

8

SAS Enterprise Miner – Interface Tour

8

Process flow

9

SAS Enterprise Miner – Interface Tour

9

Node

10

SAS Enterprise Miner – Interface Tour

10

SEMMA tools palette

11

SEMMA – Sample Tab

11

• Append

• Data Partition

• File Import

• Filter

• Input Data

• Merge

• Sample

• Time Series

12

SEMMA – Explore Tab

12

• Association

• Cluster

• DMDB

• Graph Explore

• Market Basket

• Multiplot

• Path Analysis

• SOM/Kohonen

• StatExplore

• Text Miner (optional)

• Variable Clustering

• Variable Selection

13

SEMMA – Modify Tab

13

• Drop

• Impute

• Interactive Binning

• Principal Components

• Replacement

• Rules Builder

• Transform Variables

14

SEMMA – Model Tab

14

• AutoNeural

• Decision Tree

• Dmine Regression

• DMNeural

• Ensemble

• Gradient Boosting

• Least Angle Regression

• MBR

• Model Import

• Neural Network

• Partial Least Squares

• Regression

• Rule Induction

• Two Stage

15

SEMMA – Assess Tab

15

• Cutoff

• Decisions

• Model Comparison

• Segment Profile

• Score

16

Beyond SEMMA – Utility Tab

16

• Control Point

• End Groups

• Metadata

• Reporter

• SAS Code

• Start Groups

17

Credit Scoring Tab (Optional)

17

• Credit Exchange

• Interactive Grouping

• Reject Inference

• Scorecard

18

The Analytic Workflow

18

Analytic workflow

Def

ine

anal

ytic

ob

ject

ive

Sel

ect

case

s

Ext

ract

inp

ut

dat

a

Val

idat

e in

pu

t d

ata

Rep

air

inp

ut

dat

a

Ap

ply

an

alys

is

Tran

sfo

rm in

pu

t d

ata

Gen

erat

e d

eplo

ymen

t m

eth

od

s

Inte

gra

te d

eplo

ymen

t

Gat

her

res

ult

s

Ass

ess

ob

serv

ed r

esu

lts

Ref

ine

anal

ytic

ob

ject

ive

19

SAS Enterprise Miner Analytic Strengths

19

Predictive Modeling

Pattern Discovery

20

Applied Analytics Case Studies

20

Bank usage segmentation

Web services associations

University enrollment prediction

Credit risk scoring