Business Analytics and Optimization Introduction

transcript

Business Analytics and Optimization: A Technical Introduction

Oleksandr Romanko, Ph.D. Senior Research Analyst, Risk Analytics – Business Analytics, IBM Adjunct Professor, University of Toronto

Toronto SMAC Meetup September 18, 2014

Making the world work better – pioneering the science

1973 1969

IBM Centennial: 100 Years of Innovation

Analytics Jobs

Created by: Dennis Buttera

Data science

Business Analytics

Predictive Analytics What will happen?

Descriptive Analytics What has happened?

Prescriptive Analytics What should we do?

What is analytics?

Data Insight Action

Decide Analyze

Business Value

Analytics is the scientific process of deriving insights from

data in order to make decisions

Business analytics and optimization (video)

IBM Business Analytics portfolio

IBM Business Analytics

Financial Services Public Sector Distribution Industrial Communications

Risk Customer

Industry

Solutions

Finance Operations

Risk Analytics

Business Intelligence

Software

Categories Predictive Analytics

Performance Management

Functional

Solutions

Capabilities

REPORT MODEL PREDICT COLLABORATE

Budgeting & Forecasting

Financial Consolidation

Disclosure Management

Risk Identification

Risk & Control Assessment

Resource Optimization

Social Media Analytics

Profitability Modeling &

Optimization

Production Planning

Asset Management

Customer Acquisition

Customer Lifetime

Customer Loyalty

& Retention

Risk Mitigation Planning

Risk Aware Decisioning

Sales Performance Management

PLAN ANALYZE

Visualize Discover

Forecast Mine

Govern

Decide Score

Simulate Contribute

Survey

Decision Management

Operations research

Operations Research (O.R.) is the discipline of applying advanced analytical methods to help make better decisions

Analytical techniques:

Simulation – giving you the ability to try out approaches and test

ideas for improvement

Optimization – narrowing your choices to the very best when there

are virtually innumerable feasible options and comparing them is

difficult

Probability and Statistics – helping you

measure risk, mine data to find

valuable connections and insights,

test conclusions, and make

reliable forecasts

Mathematical Modeling – algorithms

and software

Our planet is a complex, dynamic, highly interconnected $54 Trillion system-of-systems (OECD-based analysis)

Communication $ 3.96 Tn

Transportation $ 6.95 Tn

Leisure / Recreation /

Clothing $ 7.80 Tn

Healthcare $ 4.27 Tn

Food $ 4.89 Tn

Infrastructure $ 12.54 Tn

Govt. & Safety $ 5.21 Tn

Finance $ 4.58 Tn

Electricity $ 2.94 Tn

Education $ 1.36 Tn

Water $ 0.13 Tn

Global system-of-systems

$54 Trillion (100% of WW 2008 GDP)

Same Industry

Business Support

IT Systems

Energy Resources

Machinery

Materials

Legend for system inputs

1. Size of bubbles represents systems’ economic values

2. Arrows represent the strength of systems’ interaction

Source: IBV analysis based on OECD

This chart shows ‘systems‘ (not ‘industries‘)

Economists estimate, that all systems carry inefficiencies of up to $15 Tn, of which $4 Tn could be eliminated

Global economic value of

System-of-systems

$54 Trillion 100% of WW 2008 GDP

Inefficiencies $15 Trillion 28% of WW 2008 GDP

Improvement potential

$4 Trillion 7% of WW 2008 GDP

How to read the chart:

For example, the Healthcare system‘s

value is $4,270B. It carries an estimated

inefficiency of 42%. From that level of 42%

inefficiency, economists estimate that

~34% can be eliminated (= 34% x 42%).

Source: IBM economists survey 2009; n= 480

System inefficiency as % of total economic value

ntial as

f syste

m ineffic

Education

Building & Transport

Infrastructure

12,540

Healthcare

Government & Safety

Electricity

Financial

Food & Water

Transportation (Goods

& Passenger)

Leisure / Recreation

/ Clothing

Communication

Analysis of inefficiencies in the

planet‘s system-of-systems

Note: Size of the bubble indicate absolute value of the system in USD Billions

This chart shows ‘systems‘ (not ‘industries‘)

15% 20% 25% 30% 35% 40% 45%

History of analytics

History of business analytics

Business Analytics Examples

Pit stop analytics

Calculations showed that time spent changing tires and refilling the tank was more than offset by the improved performance of the car on the track. 1. Softer tires stuck to the track better during turns than their harder cousins,

though they wore out more quickly. 2. Less gas in the tank translated into a lighter, and therefore faster, car.

Optimized F1 pit teams can change four tires in two seconds

Movies

Smarter Cities

We can collect information from almost everything to make better decisions

Camera phones in

existence able to

document accidents,

damage, and crimes

1 billion RFID tags

embedded into our

world and across

entire ecosystems

30 billion Of new automobiles

will contain event data

recorders collecting

travel information

Instrumented Interconnected Intelligent

Big data

Big data are datasets that grow so large that they become awkward to work with using on-hand database management tools. Difficulties include capture, storage, search, sharing, analytics, and visualizing.

Source: Wikipedia

Big social data

Applications of big data analytics

Homeland Security

Finance Smarter Healthcare Multi-channel sales

Telecom

Manufacturing

Traffic Control

Trading Analytics Fraud and Risk

Log Analysis

Search Quality

Retail: Churn, NBO

Police use analytics to reduce crime (video)

Marketing and supply chain analytics (video)

Marketing analytics

Intelligent transport systems

Real time monitoring & forecasting of congestion in cities enables real time action to

reduce traffic and emissions – Can charge drivers at point of use for access to city centers

Stockholm Congestion Tax Project – Involves 18 barrier-free control points

– Allows differentiated pricing by time of day, congestion level, and potentially emissions level

– Results:

• Traffic reduced by 100,000 vehicle passages per day (25%)

• Public transportation passengers increased by 40,000 / day

• Congestion during peak hours and CO2 emissions were dramatically reduced

Analytics for green vehicles and technology (video)

Artificial intelligence

Source: A Brief Overview and Thoughts for Healthcare Education and Performance Improvement by Watson Team

Artificial intelligence

Source: A Brief Overview and Thoughts for Healthcare Education and Performance Improvement by Watson Team

On 27th May 1498, Vasco da Gama landed in Kappad Beach

celebrated

May 1898 400th anniversary

arrival in

In May 1898 Portugal celebrated the 400th anniversary of this explorer’s arrival in India.

Portugal

landed in

27th May 1498

Vasco da Gama

Temporal Reasoning

Statistical Paraphrasing

GeoSpatial Reasoning

explorer

On 27th May 1498, Vasco da Gama landed in Kappad Beach

On the 27th of May 1498, Vasco da Gama landed in Kappad Beach

Kappad Beach

Para-phrases

Geo-KB

Date Math

Search Far and Wide Explore many hypotheses

Find Judge Evidence

Many inference algorithms

Artificial intelligence (video)

Watson Analytics

Bluemix

www.bluemix.net

Bluemix

Business Analytics Education

IBM Academic Initiative program

Cognos SPSS ILOG

Master of Business Analytics programs – top 20 universities

Industry support for Master of Business Analytics programs

Business Analytics programs – curriculum

Applied Statistics and Probability

Fundamentals of Computational Mathematics

Data Mining and Knowledge Discovery

Simulation Modelling

Optimization

Financial Decision Making

Computational Methods for Business Data Analysis

Computational Finance and Risk Management

Visual Analytics and Knowledge Representation

Mathematical Modelling for Business

Machine Learning, Cognitive Computing and Artificial Intelligence

Marketing Analytics

Strategies for Managing Innovations

Analytics of Web, Social Networks and Business News

Applied Statistics

What kind of data are we dealing with?

Types of data

• Quantitative

• Categorical (ordered, unordered)

Data collection

• Independent observations (one observation per subject)

• Dependent observations (repeated observation of the same subject, relationships

within groups, relationships over time or space)

Type of data drives the direction of your analysis

• How to plot

• How to summarize

• How to draw inferences and conclusions

• How to issue predictions

Quantitative data

Examples: temperature, age, income

Quick check: “Does it makes sense to calculate an average?”

Appropriate summary statistics:

– Mean and Median

– Standard Deviation

– Percentiles

More advanced predictive methods: Regression, Time Series Analysis, …

Plot your data!

Summarizing quantitative data

One-number summaries

– Mean

Average, obtained by summing all observations and dividing by the number of obs.

– Median

The center value, below and above which you will find 50% of the observations.

Summarizing your data with one number may not tell the whole story:

Median = 19.8 Median = 19.8 Median = 10.5

Flaw of averages

“Plans based on average assumptions are wrong on average”

Average depth 3 ft

“Most observations fall within ±2 standard deviations of the mean.”

Standard deviation

If the data is normally distributed

95 % of observations

Standard Deviation = 4.2

~95% of observations between 11.4 and 28.2

Descriptive statistics - example

Random sample of 5000 customers of a credit card company

Amount spent on

primary card last

Debt to income

ratio (x100)

N Valid 5000 5000

Missing 0 0

Mean 1683.7340 9.9578

Median 1690.0670 8.8000

Std. Deviation 210.26680 6.42317

Minimum .00 .00

Maximum 2482.72 43.10

Percentiles

Generalizations of the median (50th percentile).

The pth is the data point below which p percent of the observations fall.

Often used to compare a single observation to a general population.

Examples:

– Standardized test scores

If you scored in the 93th percentile, your score was higher than that of 93% of test

takers.

– Child growth percentiles

Percentiles - example

Percentiles can be another way of describing how spread out data values are.

Example: 5-Number Summary

Minimum – 25th percentile – Median – 50th percentile - Maximum

Amount spent on

primary card last

Debt to income

ratio (x100)

Minimum .00 .00

Percentiles

25 1567.4658 5.1250

50 1690.0670 8.8000

75 1814.5430 13.5000

Maximum 2482.72 43.10

Distributions: Normal distribution

Distributions

Estimate of the probability distribution of global mean temperature resulting

from a doubling of CO2 relative to its pre-industrial value, made from

100000 simulations

Questions?

Business Analytics and Optimization Introduction

Technology