75
1 1 The Landscape – Analytics and Data Science

Data Science-final7

Embed Size (px)

Citation preview

Page 1: Data Science-final7

1 1

The Landscape – Analytics and Data Science

Page 2: Data Science-final7

2 2

When I say big data which of these describes what you feel?

Page 3: Data Science-final7

3 3

When I say big data which of these describes what you feel?

Page 4: Data Science-final7

4 4

When I say big data which of these describes what you feel?

Page 5: Data Science-final7

5 5

When I say big data which of these describes what you feel?

Page 6: Data Science-final7

6 6

When I say big data which of these describes what you feel?

Page 7: Data Science-final7

7 7

When I say big data which of these describes what you feel?

Page 8: Data Science-final7

• Well, this talk is NOT about big data, but what it can do for you

• On the way, you might just gain some clarity of terms, and technologies

8 8

Big Data

Page 9: Data Science-final7

• The quantity of data allows the five pillars of analytics to become empirical sciences

• If used right, business and medical goals are substantially bettered

• It is not just about knowing more, it is about zeroing in on the truth

• We will talk about they ways people miss the truth, even seeming to use current best practices

9 9

Big Data

Page 10: Data Science-final7

10 10

Page 11: Data Science-final7

11 11

Page 12: Data Science-final7

• I like to start with the business questions, the business and medical practice needs, what leaders of businesses and medicine would most like to do

12 12

The Big Questions

Page 13: Data Science-final7

• Who, where, what, how, and how much for each group

13 13

Who, where, what, how, and how much

Page 14: Data Science-final7

• Business is about action, doing. Just do it! But what to do, and to whom, and with what, and what channel?

• What are the choices that maximize results and ROI?

14 14

Just do it, to maximize results and ROI

Page 15: Data Science-final7

• Global Goal Driven Dynamic Demographics for Proaction Optimization (G2D3PO or just D3PO)

• What Group?• What Actions?• Global Goal: Profit, Customer Satisfaction,

Manufacturing Excellence, Reduced Community Healthcare Costs, etc.

15 15

Global Goal Driven

Page 16: Data Science-final7

16 16

Why these arbitrary fixed groupings?

Page 17: Data Science-final7

• Groupings, affiliations and interests depend on goals and context

• Arbitrary bounds to ranges are just assumptions that can totally change how statistics come out and our view of the world

• Bad assumptions lead to bad decisions • Data discovered and confirmed foundations

lead to good decisions

17 17

Global Goal Driven

Page 18: Data Science-final7

18 18

Case Study – Large Retail Bank – Customer Service Screen

Page 19: Data Science-final7

19 19

Goal: Sell Product – Top Pain Found and DefinedOptimal Grouping and Action

Page 20: Data Science-final7

20 20

Case Study – Large Retail Bank Targeted Allegiance Maintenance

Page 21: Data Science-final7

• Before: 0.07% conversion rate for new product proposals – “shotgun” marketing

• After: 7%– A 100X increase in closure rate– $1B increase in new product the first year – Rising even faster the second year– “Good customer” attrition rate down 6% • $200M annual saving from this churn mitigation

21 21

Case Study – Large Retail Bank

Page 22: Data Science-final7

• Almost no lift from “shotgun” marketing approach

22 22

What is new and different? -- Old Profit Lift Curve

Page 23: Data Science-final7

• The state of the art predictive approach: Ranking via scores

23 23

What is new and different? – State of the Art Profit Lift Curve

Page 24: Data Science-final7

• Global Goal Driven Dynamic Demographics for Proaction Optimization• Spending only as much as needed to acquire

24 24

What is new and different? -- D3PO Lift Curve

Page 25: Data Science-final7

• Groupings are generated appropriate for the sale of each product

• The best of multiple offer opportunities is chosen

• The best proposal opportunities first• Product, offering, or discount proposals based

on expected long-term value to company• Cost of acquisition more focused

25 25

Improvements come for three reasons:

Page 26: Data Science-final7

26 26

Case Study – Hospital /Managed Care

Page 27: Data Science-final7

27 27

Managed Care – Group Based on Goal: Increase population Health

Page 28: Data Science-final7

28 28

Hospital /Managed Care – Personalized Recommendations

Page 29: Data Science-final7

• Static: Statistical Reports• Interactive Descriptive: BI• Predictive: Learning Algorithms (LA)• Prescriptive: Decision Classes or Optimization• Proactive: Optimizing Groups

29 29

The Progress

Page 30: Data Science-final7

• To the business user the technology should just be something that happens in the background

• At the same time, how the recommended decisions are being made should be transparent to the managers

30 30

The Best Thing for Business and Medical Analytics

Page 31: Data Science-final7

31 31

This is a talk about:

• How Big Data can enable Data Science to be a true science

• The large opportunities it can offer for generating value for companies and healthcare

• How we only can know, see and forecast because we have assumptions, assumptions that can be wrong

• But what makes the empirical method work is the process of testing and revising assumptions to discover the real world

Page 32: Data Science-final7

• What business and healthcare providers want • How BI, and Advanced Analytics depends on assumptions• How easy it is to attribute too much intelligence to artificial

intelligence• True intelligence is bound up with the ability to recognize

and revise assumptions• That methods of grouping are always multiple • How the generation of action classes (or Proaction classes)

to appreciate groups of people (or resources) for a given goal is the method to add great value to business and healthcare

32 32

We will also recognize:

Page 33: Data Science-final7

33 33

Revising assumptions changes your world

Page 34: Data Science-final7

34 34

Different categorizations for different goals

Page 35: Data Science-final7

35 35

Different categorizations for different goals

Page 36: Data Science-final7

36 36

Arbitrary Assumptions -- Age vs. Income breaks

Page 37: Data Science-final7

37 37

Arbitrary Assumptions -- Age vs. Income breaks

Page 38: Data Science-final7

38 38

Arbitrary Assumptions -- Same People Different Understandings

Page 39: Data Science-final7

39 39

The interesting cluster cannot even be seen by slice and dice methods

Page 40: Data Science-final7

40 40

Both the human eye and LA’s must make assumptions to see at all assumptions that circumstances can reveal

Page 41: Data Science-final7

41 41

Both the human eye and learning algorithms can impose readings that make no sense

Page 42: Data Science-final7

42 42

Both the human eye and learning algorithms can miss important hidden patterns

Page 43: Data Science-final7

43 43

Real Intelligence is knowing how to collect the added data to know what is really going on, like throwing a rock at the lava

Page 44: Data Science-final7

• What is Data Science?

44 44

Humans are natural pattern recognizers We project out inner patterns and assumptions on the universe

Page 45: Data Science-final7

45 45

So do learning algorithms and many of the modeling methods

Page 46: Data Science-final7

46 46

These are random dots

Page 47: Data Science-final7

47 47

Our eye just naturally finds meaningless clusters

Page 48: Data Science-final7

48 48

Learning algorithms and modeling have built in assumptions too

Training on first half of the flight of a baseball

Attempting to predict 2nd half

Page 49: Data Science-final7

49 49

Built in assumptions – Flight of a Baseball – Non-representative data

Error

Page 50: Data Science-final7

50 50

Non-representative data

Page 51: Data Science-final7

51 51

Non-representative data

Page 52: Data Science-final7

52 52

Baseball fit – Error from just assumptions of mathematical form

Error

Page 53: Data Science-final7

• Data generated by people, such as in markets or from buying behavior, has far more noise than a physical system such as a baseball’s flight

53 53

Page 54: Data Science-final7

54 54

What is the pattern hidden in the noise?

Page 55: Data Science-final7

55 55

What is the pattern hidden in the noise?

Page 56: Data Science-final7

56 56

What is the pattern hidden in the noise?

Page 57: Data Science-final7

57 57

What is the pattern hidden in the noise?

Page 58: Data Science-final7

58 58

What is the pattern hidden in the noise?

Page 59: Data Science-final7

59 59

What is the pattern hidden in the noise?

Page 60: Data Science-final7

60 60

What is the pattern hidden in the noise?

Page 61: Data Science-final7

61 61

What is the pattern hidden in the noise?

It is a sine (sign)

Page 62: Data Science-final7

62 62

The Landscape – Analytics and Data Science

Page 63: Data Science-final7

63 63

Descriptive StatisticsBI, Dashboards, Scorecards, Reporting, Discovery, What-if

Page 64: Data Science-final7

64 64

Predictive Analytics – Learning Algorithms – Forecast Techniques

Page 65: Data Science-final7

• Taking historical data samples and finding patterns using learning algorithms to project what will happen in the future, or to new individuals to detect opportunities, differences, or abnormalities

65 65

Predictive Analytics

Page 66: Data Science-final7

66 66

Network Analytics – Social – Information

Page 67: Data Science-final7

• Measuring and creating statistics about the processes that connect individuals or technology in potentially a complex web of interactions

67 67

Network Analysis

Page 68: Data Science-final7

68 68

Modeling – Simulation -- Mapping

Page 69: Data Science-final7

• Developing a language, potentially mathematical, whose characteristics and relationships have close analogies and structure to something in the real world.

69 69

Modeling

Page 70: Data Science-final7

70 70

Optimization

Page 71: Data Science-final7

• The process were the best or near best of potentially an infinite number of options are chosen or found relative to a goal

71 71

Optimization

Page 72: Data Science-final7

• Network Optimization

• Predictive Modeling

• Predictive Optimization

72 72

Advance Analytics – Any of the above can be combined

Page 73: Data Science-final7

73 73

D3PO combines all four advanced analytic methods

Page 74: Data Science-final7

74 74

Big data allows us to more carefully follow scientific empirical methods honed over 200 years to find the truth

Page 75: Data Science-final7

75 75

More next time about how our LA’s implicit assumptions fail us and how Big Data can help to do it right to get valuable results