Data Science

INTRODUCTION TO DATA
SCIENCE
Introduction and Administration
Plan
requirements
Why data science

is important?
What is data
science?
What this course

is about?
Course
homework assignments
• Homepage, contact details
• “Why are you here”
• Mashup of
disciplines
• Hopefully right mix of

theory and practical
skills
• Syllabus
• Grade ,exam,
1. Why are you here?
Introduction: Media Buzz
Data Scientists are in high demand
Also in Academia
Demand will outpace the supply
Israel
Pays well
2. What is data science?
Technology and raising expectations
Data Science



New Discipline 



Very little/none textbooks/courses

covering
 the discipline as a whole

Compare to Software Engineering/Compute Science during

 70-80s of the last century
 
 Data Science is what data scientists do


 Why data science and data scientists are needed? 
  Development of enabling technology 
 
Raising Expectations from customers
Technological developments
Declining cost of storage
Declining cost of computing
Surpassing the brain
More data can be stored and processed
Value of Big Data
Devices vs. People
Internet of Things
Next frontier: IoT
Raising expectations
Cognitive Computing

 People expect systems to behave like humans 
 
 Be Adaptive
 
 Learn as information and goals change
 
 Be Interactive
 
 Interact easily with people and other systems
 
 Be Contextual
 
 Understand meaning, exploit additional sources of information




Need to process large quantities of uncertain data of
different types (text, speech, sensors, images etc.) 
Cognitive and Data Science

People want their systems/devices to
 behave smarter 

 Personal devices 
 
 Industrial systems





More data to acquire and analyze using
more complex algorithms and technologies 
3. What is data science
Some examples
Example I: Marketing

 Predicting Lifetime Value (LTV) 

what for: if you can predict the characteristics
of high LTV customers, this supports customer
segmentation, identifies upsell opportunities and

 supports other marketing initiatives 




usage: can be both an online algorithm and a static 
report showing the characteristics of high LTV customers
Example II: Logistics

 Demand forecasting 

How many of what thing do you need and where
will we need them? (Enables leaninventory and
 prevents out of stock situations.)

revenue impact: supports growth and militates
 against revenue leakage

usage: online algorithm and static report 
Example III: Healthcare

 Survival analysis 

Analyze survival statistics for different patientattributes
 (age, blood type, gender, etc) and treatments



 Medication (dosage) effectiveness 

Analyze effects of admittingdifferent types and dosage
 of medication for a disease



 Readmission risk 

Predict risk of re-admittance based on patient 
attributes, medical history, diagnose & treatment
Example IV: Wearable Health and
Fitness
Example V: Brain Computer Interface
A Mashup of disciplines
A mashup of disciplines
Math and Theory • Statistics, Linear Algebra, Optimization,

Time Series, etc.
Applied Algorithms • Machine Learning, Data Structures,

Parallel Algorithms, etc.
Engineering and • Storage and computing platforms,

Technologies statistical tools ,etc.
Domain Expertise • Text, Finance, Images, Econometrics etc.
Art • Visualization, Infographics
Best practices • Handle missed values in data, transform

and hacks and represent data, etc.
Yet Another View
Types of Data Scientists
Roles and Paycheck
3. About this course
A mix of theory and practice
General

 Introductory course 
 
 But for advanced undergrads




 Broad overview of subjects 
 
 But deep enough to have an exam




 Focus on practical aspects 
 
But not on ever-changing technology and tools
Tentative content(subject to change)

 70% Statistical Machine Learning (7 weeks) 
  Focus on practical aspects 
  Classes 
  
Necessary theoretical background
 
 Basic R programming lab


 20% Big Data Algorithms (2 weeks) 
 
 Focus on algorithms not on big data technologies


 10% Data Visualization (1 weeks) 
 
Grammar of graphics in R
This course is not

 About big data tools or technologies 
  No: Hadoop technical details 
 
 Yes: Basic R programming


 About statistical learning theory 
  No: Theoretical low bounds or other proofs 
 
 Yes: Some theory is necessary


 About a specific domain 
  No: Deep discussions on Text, Finance, BI etc. 
 
Yes: Some examples will be presented
Some case studies we will cover
PREDICTION OF
FUTURE MOVEMENTS • What is the next move of S&P 500?
IN THE STOCK MARKET:
PREDICTING INSURANCE
PURCHASE • Will a potential customer purchase?
DIRECT MARKETING • Who will respond?
HOUSING VALUATIONS • What affect the price of a house?
MARKETING OF ORANGE
JUICE • What brand a customer will buy?
EMAIL SPAM • Is this a spam message?

The course’s language of choice: R
What you are expected to know

 Data is represented as a matrix 

 Basic linear algebra 



 Most problems are not well-defined/uncertain 

 Basic probability and statistics 



 Big data requires non-trivial data structures and algorithms 

 Basic data structures and algorithms concepts 



 Practical means programming 

Basic Programming skills 
Textbooks are available online
Machine Learning and R Big Data Algorithms

Visualization
Introduction from On-going examples

For curious minds
More on Machine Learning More on R Programming

Becoming a data scientist
Data Scientist Skills Quick Hacks/Examples

4. Course requirements
Requirements
 
 Grade
 
 100% closed material exam




 No previous year exams 
 
 Both textbooks have after chapter exercises

Exam questions (and HW assignments) will

 be very similar to these questions



See course homepage for HW submission guielines 
Plan
requirements
Why data science

is important?
What is data
science?
What this course

is about?
Course
homework assignments
• Homepage, contact details
• “Why are you here”
• Mashup of
disciplines
• Hopefully right mix of

theory and practical
skills
• Syllabus
• Grade ,exam,
Few More Disclaimers
Very inaccurate explanation

Statistics: take a sample (data), answer questions about the
process that produced this sample

 Is it a normal distribution? Estimate it’s mean. 



Machine Learning: take a sample(data),

build a model to answer
 questions about future samples
 
 Given a sample of named faces, design a model for naming a new unseen face.


 Data Mining: mine huge data store for interesting patterns or relationships 

Given DBof transactions, apply tools and algorithms to find frequent product
 bundles


 Data Science: do whatever necessary to extract value from the data 

Use data to improve book sales: mine patterns,  engineer recommender
systems, suggest improvements, estimate impact
No clear-cut boundaries!
Disclaimer: Math in the course



All the computation are performed by computer 




You are in charge for interpretation of numbers 


 So you’ll have to understand the logic behind the number 

 You’ll see significant amount formulas during the course 

 Mostly arithmetic, matrices and probability 




You are not expected to memorize or derive each
 formula (with exceptions), but you are expected to 
 
Understand its meaning and use

Data Science

Uploaded by

Copyright:

Available Formats

Data Science

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Data Science

Uploaded by

Copyright:

Available Formats

INTRODUCTION TO DATA

Why data science

What this course

• “Why are you here”

• Hopefully right mix of

Math and Theory • Statistics, Linear Algebra, Optimization,

Applied Algorithms • Machine Learning, Data Structures,

Engineering and • Storage and computing platforms,

Domain Expertise • Text, Finance, Images, Econometrics etc.

Art • Visualization, Infographics

Best practices • Handle missed values in data, transform

DIRECT MARKETING • Who will respond?

HOUSING VALUATIONS • What affect the price of a house?

EMAIL SPAM • Is this a spam message?

Machine Learning and R Big Data Algorithms

Introduction from On-going examples

More on Machine Learning More on R Programming

Data Scientist Skills Quick Hacks/Examples

Why data science

What this course

• “Why are you here”

• Hopefully right mix of

You might also like