• No results found

Predictive Analytics: Turn Information into Insights

N/A
N/A
Protected

Academic year: 2021

Share "Predictive Analytics: Turn Information into Insights"

Copied!
46
0
0

Loading.... (view fulltext now)

Full text

(1)

Predictive Analytics:

Turn Information into Insights

Pallav Nuwal

Business Manager; Predictive Analytics, India-South Asia

[email protected] +91.9820330224

(2)

Confidential to IBM

Agenda

 IBM Predictive Analytics portfolio

 Predictive Analytics for Industry Verticals

 Key Features

(3)

© 2012 IBM Corporation Source: IBM Global CEO Study 2012

IBM CEO Study 2012

(4)

Enabling the Predictive Analytics Process

4

Collaboration and Deployment Services

CCI

Data Collection

Modeler Decision

Management Statistics

Transactions Demographics

Interactions Opinions

Predictive Modeling Data Mining Text Analytics Social Network Analysis

Statistical Analysis

Prediction Rules Optimization

Process

Detect & Capture Analyze & Predict Engage & Act

(5)

Predictive Analytics for your

Business

© 2011 IBM Corporation 5

(6)

Confidential to IBM

6

Attract, Grow and

Retain Top

Performers

Advanced Analytics for Large Enterprises

Monitor, Detect and

Control Fraud

Achieve Sales

Excellence

Ticket Data

Analytics

- Project

Analytics

(7)

Confidential to IBM

7

Manufacturing

Predictive Maintenance

Sales Forecasting

Advanced Analytics for your business

Automotive

Warranty Analytics

Dealer Analytics

Telecom

Customer Churn Analytics

Cross Sell/ Upsell

Campaign Analytics

Network Optimization

Retail

Market Basket Analytics

Assortment planning /

Merchandising

(8)

Confidential to IBM

8

Advanced Analytics for BFSI

Analyze and

Predict

Customer Analytics:

• Profile Your Customers

• Credit Scoring & Internal Rating

• Use RFM Scoring

• Cross-Sell Up-sell

• Retain Profitable Customers

Fraud & Risk Analytics:

• Credit Risk Scoring

• Anomaly Detection

Operations Analytics:

• ATM Cash Management

• Agent Analytics

(9)

Confidential to IBM

9

1: Tax Fraud Prediction and Prevention

3: Department of Economics and Statistics

IBM Predictive Analytics Use Cases for Governments

2: Crime Prediction and Prevention

(10)

© 2012 IBM Corporation 10

Data Collection for Market

Research

© 2011 IBM Corporation 10

(11)

Market Analysis

2011 Analyst Reports

11

“IBM’s vision of a ‘smarter planet’

is where the future of EFM is heading, and IBM SPSS has provided the benchmark for what it looks like.”

Forrester Research

© 2012 IBM Corporation

“When we benchmark the market- insights-focused EFM vendors against Forrester’s

EFM definition, IBM SPSS excels with every aspect of the

definition.”

Forrester Research

IBM SPSS Data Collection for Market Research

(12)

© 2012 IBM Corporation

SPSS Data Collection

A complete, integrated survey platform

12 © 2012 IBM Corporation

IBM SPSS Data Collection for Market Research

(13)

Social Media Analytics

© 2011 IBM Corporation 13

(14)

IBM Confidential

Solution Capabilities

IBM Social Media Analytics & Predictive Analytics

BLOGS BLOGS

DISCUSSION FORUMS DISCUSSION FORUMS

NEWSGROUPS NEWSGROUPS

FACEBOOK TWITTER

&/OR OTHER SOCIAL MEDIA

FACEBOOK TWITTER

&/OR OTHER SOCIAL MEDIA

Source Areas

 Dimensional Analysis

 Filtering

 Keyword Search

 Dimensional Navigation

 Drill Through to Content

 Relevant Topics

 Associated Themes

 Ranking and Volume

 Relationship Tables

 Relationship Matrix

 Relationship Graph COMPREHENSIVE

ANALYSIS

SENTIMENT

EVOLVING TOPICS AFFINITY ANALYTICS

Business Drivers

Customer Care Customer Care Corporate Reputation

Corporate Reputation Campaign Effectiveness

Campaign Effectiveness Competitive Analysis

Product Insight

PREDICTIVE ANALYSIS

 Predict impact of sentiment on business KPI’s &

KPP’s

 Predict sentiment on future social media activities and channels

14

(15)

IBM SPSS Statistics 21

© 2011 IBM Corporation 15

(16)

16

Predict: IBM SPSS Statistics

 Advanced statistics and data management for analysts

researching business problems

 Collection, analysis,

interpretation, explanation and presentation of data

 Provides insight into a sample of data and tools for prediction and forecasting based on the data

Drives confidence in your results and decisions

Drives confidence in your results and decisions

(17)

Monte-Carlo Simulation

 Included in IBM SPSS Statistics Base

 Simulate data according to user- specified parameters

 Uses simulated data as input to predict an outcome

 ‘Tweak’ parameters used to simulate the data, and compare outcomes

– Example, simulate the number of sales agents and see how it affects in achieving a specific target.

 Ability to perform “what if” scenarios

(18)

IBM SPSS Statistics 21 provides a unique analytics approach to

Monte Carlo Simulation

 Automatically calculate user-specified parameters

 Support the use of Predictive Models to calculate outcomes

 Lets you start from an existing model

 Used across many sectors:

Finance: Understand uncertainty associated with investment planning.

Manufacturing: Determine how the cost of materials affects profit.

Advertising/marketing/profession al services: Simulate various advertising budget amounts to see the effect on total sales.

Energy and utilities: See how

(19)

IBM SPSS Modeler Overview

© 2011 IBM Corporation 19

(20)

IBM SPSS Modeler

• Easy-to-use, interactive interface without the need for programming

• Automated modeling and data preparation capabilities

• Access ALL data – structured and unstructured – from disparate sources

• Natural Language Processing (NLP) to extract concepts and sentiments in text

• Entity Analytics ensures the quality of the data and results in more accurate models

• Leverage existing investment in Cognos, Netezza, InfoSphere and System Z

(21)

© 2012 IBM Corporation 21

Entity Analytics

© 2011 IBM Corporation 21

(22)

© 2012 IBM Corporation 22

Is this one person or two?

Entity Analytics automatically detects when multiple entities are the

same despite having been described differently.

(23)

© 2012 IBM Corporation 23

Entity Analytics uses “Context Accumulation” to Find Deeper Insights

Not Actionable

“Product is Awful #TheCo”

1 minutes ago

Substantially more Actionable

“Product is Awful #TheCo”

1 minutes ago Influential

@Twitter

Call Center Complaint

Terminated Employee

Context: Better understanding something by taking into account the things around it

Context Accumulation: The incremental process of integrating new observations with previous observations

(24)

© 2012 IBM Corporation 24

IBM SPSS Entity Analytics Delivers General Purpose “Context

Accumulation”

Observation Space

Information In Context

Consumption

Data Finds Data

Entity Analytics

Relevance Finds User

(25)

© 2012 IBM Corporation 25

Entity 102

Name Beth L. Johns -Parker BL Johns

Addr1 123 Main Street 777 Park Road

City New York

State NY

Phone 2127331234 DOB 6/21/1954 Income $8,000 Credit Debt $5,359 Other Debt $2,009 Debt to Income 92.1 Prev Default? True Pending Loan False

Name Elizabeth Lisa Johns Liz Johns

Beth L Johns-Parker BL Johns

Addr1 123 Main Street 777 Park Road 33 Red Dr 33 Reed Dr

City New York,

White Plains, Mamaroneck

State NY

Postal 11732, 10354 Phone 212-733-1234

914-698-2234

DOB 6/21/1954

Defaults Yes

Income $48,000 Credit Debt $12,722 Other Debt $9,009 Debt to Income 113.5 Prev Default? True Pending Loan True

Resolved Entity Entity 343

Full Liz Johns

Addr1 33 Red Dr

City Mamaroneck

State NY

Postal 10354 Phone 212-733-1234

914-698-2234 Income $9,000

Credit Debt $6,000 Other Debt $3,000 Debt to Income 100 Prev Default? True Pending Loan False

Full Elizabeth Lisa Johns Addr1 33 Reed Dr

City White Plains

State NY

Postal 10354 Phone 914-698-2234 Income $31,000 DOB 6/21/1954 Credit Debt $1,362 Other Debt $4,001 Debt to Income 17.3 Prev Default? False Pending Loan True

Entity 642

Entity Analytics – Application for Credit

(26)

© 2012 IBM Corporation 26

Text Analytics

© 2011 IBM Corporation 26

(27)

© 2012 IBM Corporation 27

Text Analytics Identifies the Context/Sentiment of the Text

Text Analytics Extracts Concepts and Patterns from Text

(28)

© 2012 IBM Corporation 28

Social Network Analysis

© 2011 IBM Corporation 28

(29)

© 2012 IBM Corporation 29

Social Network Analysis Applications

Churn Prediction

 Group characteristics can influence churn rates

 Focus on individuals in groups with an increased risk of churn

 Identify individuals that are at risk of churning due to the flow of info from those that already churned.

Leveraging Group Leaders

 Group leaders are highly influential over other group members

 Prevent a group leader from churning to decrease the churn rate for other group members

 Acquire a group leader from a competitor to increase the churn rate that group.

Marketing

 Use Group leaders to initiate new goods or service offerings.

(30)

© 2012 IBM Corporation 30

Modeler Server

© 2011 IBM Corporation 30

(31)

© 2012 IBM Corporation 31

In-Database Support with SPSS Modeler Server

 All the features of IBM SPSS Modeler

 Large volumes of data

 High performance

 Administration and security options In-Database via…

 SQL pushback

 In Database Algorithms

 Scoring Adapters

 SQL scoring

(32)

© 2012 IBM Corporation 32

Collaboration & Deployment

Services

© 2011 IBM Corporation 32

(33)

Collaboration and Deployment Services

Manage and deliver more effective analytical results

Share: Need to centralize and share analytical assets

Protect: Automatically tracking and auditing changes

Publish: Easy for business users to access results formerly

reserved for analysts

33

Deliver scores: Optimized for real time

Integrate: Programmatic interfaces into operational systems

Enterprise ready: Ensures scalability, reliability, security

Construct: Complex jobs, different scenarios, multiple tools

Operationalize: Monitor results

Govern: Managed changes; Audit ready

Automation

Collaboration

Deployment

(34)

Analytical Decision Management

© 2011 IBM Corporation 34

(35)

IBM Analytical Decision Management

Better outcomes in real-time, Every time.

Empowers business users

Real-time adaptive decisions to accommodate changing conditions

Provides recommended actions



Predictive analytics +



Business rules +



Scoring +



Optimization techniques

35

(36)

© 2012 IBM Corporation 36

Integration with Other IBM Products

© 2011 IBM Corporation 36

(37)

© 2012 IBM Corporation 37

Adding Value to Cognos BI with Predictive Analytics

3) Results widely distributed via BI for consumption by Business Users

Cognos BI

Common Business Model

1) Leveraging BI, identify problem or

situation needing attention 2) Use SPSS predictive

analytics & feed

results back into the BI layer

(38)

Confidential to IBM

IBM SPSS in India

Manufacturing

• Sales Forecast Analysis

• Inventory Management

Education

• Student retention

• Curriculum optimization

• Alumni management

IT/ ITES

• Employee retention

• Customer Insights

Government

• Crime Prediction & Prevention

• Tax Fraud Analytics

• Economics and Statistics Departments

Banking

• Customer Analytics

• Risk Analytics

Insurance

• Cross Sell/ Up Sell

• Persistency Analysis

(39)

© 2012 IBM Corporation 39

Why IBM Predictive Analytics

© 2011 IBM Corporation 39

(40)

Confidential to IBM

40

1: Complete Analytics Platform

3: Focus on Business Users

Why IBM Predictive Analytics?

2: Ease of use

4: Lower Total Cost Ownership

5: IBMs focus on Analytics

6: Our proven success in India

(41)

© 2012 IBM Corporation

Thank You

Pallav Nuwal

Business Manager; Predictive Analytics, India-South Asia

[email protected]

+91.9820330224

(42)

Confidential to IBM

42

Predictive Analytics: 2012 Forrester Wave

• Products

• Licensing

• Market Reach

• The IBM advantage

(43)

© 2012 IBM Corporation

SPSS Data Collection

Key benefits

 Create a survey which will reach

all constituents, regardless of

language or location

 Control the entire survey

process – from design and

interviewing through to analysis

and reporting

 Apply real-time logic and data

validation to ensure clean, high

quality data

 Leverage advanced analytical

capabilities through integration

with SPSS Statistics and

SPSS Modeler

43 © 2012 IBM Corporation

(44)

© 2012 IBM Corporation

SPSS Predictive Analytics Software

4 Key Categories

44

Data Collection

Delivers accurate view of customer attitudes & opinions

IBM SPSS Data Collection

Statistics

Drives confidence in your results & decisions

IBM SPSS Statistics

Modeling

Brings repeatability to ongoing decision making

IBM SPSS Modeler

IBM SPSS Text Analytics

Deployment

Maximizes the impact of analytics in your operation

IBM SPSS Decision Management

IBM SPSS Collaboration & Deployment Services

(45)

Confidential to IBM

45

Social Media Surveillance

Predictive Threat Management

Intelligence Analysis

& Insider Threat

Detection

Crime Prediction

and Prevention

Crime Prediction and Prevention

Data Breach

Investigations &

Prediction

Border Security/

Protection

Surveillance

Detection

Signals Analysis

Battle Space

Awareness

(46)

Confidential to IBM

46

Leverage available

information

Tax Fraud Detection and Prevention

Segment & Profile

dealers

Analyze and

Predict Fraud

Learn to get

better

References

Related documents

Product Name: Advanced Analytics Market (Big Data Analytics, Social Analytics, Visual Analytics, Customer Analytics, Risk Analytics, Business Analytics, Statistical Analysis,

Among several scholars who claim the strengths of using blogs as a teaching and learning tool in education, Campbell (2003) states that there are three types of

Our highly skilled Color Specialists will carry out an in-depth bespoke complimentary color consultation; advising you on the colors and techniques most suitable for you and your

They are leveraging, with great success, predictive modeling for customer analytics, people analytics, operational analytics, and digital/social analytics applications.. They are

to the teaching and learning English to solving the students‘ difficulties in writing a descriptive text and to make the teacher choose this method to improve students‘.. ability in

compositional differences between age groups in asthma severity and other unobserved factors. However, the results of our cross-sectional analyses were consistent with the results

(a) Single-sided displacement spectra measured by the in-loop homodyne detector, at different electronic gains g el.. We exclude three narrow spectral features from the analysis