predictive analytics pa wc conf june 2017 final.pptx [read ...€¦ · predictive analytics •...

71
1

Upload: others

Post on 06-Jun-2020

1 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

1

Page 2: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

AGENDA

What is predictive analytics?What is data mining?What is big data?What is a data scientist?

How big data is leveraged to save lives

Advanced math – moving away from linear models of data analytics

Predictive analytics in claims and underwriting

Questions

2

Page 3: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

WHAT IS PREDICTIVE ANALYTICS?

Predictive analytics describes any approach to data mining with four attributes:

An emphasis on prediction, rather than description, classification or clustering Rapid analysis measured in hours or days, rather than the

stereotypical months of traditional data mining An emphasis on the business relevance of the resulting insights -

no “ivory tower” analyses An emphasis on ease of use, thus making the tools accessible to

business users.

3

Page 4: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

4

WHAT IS DATA MINING?

Data mining is an interdisciplinary subfield of computer science. It is the computational process of discovering patterns in large data sets involving methods at the intersection of artificial intelligence, machine learning, statistics, and database systems.

Page 5: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

WHAT IS BIG DATA?

Big data is a term for data sets that are so large or complex that traditional data processing applications are inadequate. Challenges include analysis, capture, data curation, search, sharing, storage, transfer, visualization, querying, updating and information privacy.

5

Page 6: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

6

A data scientist is someone who blends math, algorithms, and an understanding of

human behavior with the ability to hack systems together to get answers to

interesting human questions from data

What is a Data Scientist?

Page 7: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

How Big Data is Leveraged To Save Lives

Kent Szalla

7

Page 8: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Agenda 

• Predictive Analytics• How  to get started ‐ Vision Strategy Plan (VSP) • Prerequisites for Success • Closing

8

Page 9: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Predictive Analytics

• Not:– Standard statistical analysis– Actuarial science

• Ingredients:– Lots of data– Lots of processing power– Tools (Tensorflow, R, JSAT, IBM, etc.)– Data scientists– Domain knowledge– CrowdFlower definition: AI=TD+ML+HITL

9

Page 10: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Predictive Analytics

• Where:– Everywhere

• Who:– Google– Uber– PeopleNet– Othot

10

“Machine learning...is the next transformation...[it] will be the basis and fundamentals of every 

successful huge IPO win in 5 years.” – Eric Schmidt, Google Executive Chairman

Page 11: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

11

VisionVSP

StrategyPlan

Goal

Logic to reach Goal

Steps to reach Strategy

Page 12: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

12

Vision ‐ GoalWhat we want to accomplish

Why does a company implement a Safety Program?

Protect Life & Reduce Costs

Page 13: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

13

Strategy – LogicHow we reach our goal

How can we Protect Life & Reduce Costs?

Reduce & Control Risk

Page 14: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

14

Plan ‐ Steps

• Understand our vulnerabilities• Create action plan to mitigate

Steps to implement our Strategy

How can we Reduce & Control Risk?

Measure risk (historical and potential)

Page 15: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

15

VisionVSP

StrategyPlan

• Protect Life & Reduce Costs

• Reduce & Control Risk

• Measure Risk• Action Plan

Page 16: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

16

What metrics do we measure?

• Incidents/Injuries• Near Hits• Types (FA vs Recordable)

• Inspections• Observations• Observers

• Wt. % Safe• Late Fixes• Indexing

Measuring Risk

Historical Risk Engagement Quality

Page 17: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

17

What granularities do we measure?

Measuring Risk

Locations

Workers / Contractors

Observers

Page 18: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

18

Metrics

• Incidents/Injuries• Near Hits• Types (FA vs Recordable)

• Inspections• Observations• Observers

• Wt. % Safe• Late Fixes• Indexing

Measuring Risk

Historical Risk Engagement Quality (Inspection)

GranularitiesLocationsWorkers / ContractorsObservers

How much data is this?

Page 19: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

19

In a given month…

Granularity # of Levels

Locations

Workers / Contractors

Observers

Total

Page 20: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

20

25

30

35

40

Monthly Trend for Average CompanyLocations Past 12 Months

20

37

Page 21: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

50

55

60

65

70

75

80

85

Monthly Trend for Average CompanyWorkers / Contractors Past 12 Months

21

77

Page 22: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

0

20

40

60

80

100

120

Monthly Trend for Average CompanyObservers Past 12 Months

22

93

Page 23: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

23

In a given month…

Granularity # of Levels

Locations

Workers / Contractors

Observers

Total

Page 24: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

24

In a given month…

Granularity # of Levels

Locations 37

Workers / Contractors 77

Observers 93

Total 207

Metric Type # of Metrics

Historical Incidents 6

Engagement 5

Quality 22

Total 33

207 Granularities  X 33 Metrics 6,831 Data Points=

Page 25: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

25

How much information can the brain handle at one time?

The information you can hold in your mind at one time is the information you can interrelate.

Nelson Cowan, Ph.D. PsychologyProfessor Univ. Missouri‐Columbia

4Answer:

< 6,831

Page 26: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

26

Problem

4 6,831

Mind’s LimitInformation to 

Process

<

Problem Solver (Data Scientist)

Page 27: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

27

How can a Data Scientist help?

6,831 1

Page 28: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

28

Prediction

Condense Information Measure Risk

Plan • Measure Risk• Action Plan

Page 29: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

29

Interpreting Prediction

Probability

An injury is likely to occur

Page 30: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

30

Interpreting Prediction

Probability

80% Chance of Rain

80% Chance of Injury

Page 31: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

31

Interpreting Prediction

Project Risk

Palo Construction

RFK Bridge

OPD Headquarters

One Life Way

National Harbor

Flag

Page 32: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

32

Interpreting Prediction

Project Risk

Palo Construction 20%

RFK Bridge 95%

OPD Headquarters 10%

One Life Way 50%

National Harbor 80%

Page 33: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

33

What else can we do with Probabilities?

Grouping

0% 100%33% 66%

0% 100%50% 80%

0% 100%70%

Not Likely

Very Likely

Page 34: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

34

Project Risk

Palo Construction 20%

RFK Bridge 95%

OPD Headquarters 10%

One Life Way 50%

National Harbor 80%

What else can we do with Probabilities?

Grouping

Page 35: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

35

Project Risk

RFK Bridge 95%

National Harbor 80%

One Life Way 50%

Palo Construction 20%

OPD Headquarters 10%

What else can we do with Probabilities?

Ranking

Page 36: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

0%

25%

50%

75%

100%

Location Probability TrendsRFK Bridge National Harbor

36

What else can we do with Probabilities?

Trending

Page 37: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

37

What else can we do with Probabilities?

Aggregation

Page 38: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

38

Measure Risk

Plan • Measure Risk• Action Plan

GroupingRankingTrendingAggregation

Page 39: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

39

Plan • Measure Risk• Action Plan

How do we come up with an Action Plan?

Page 40: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

40Metric 1

Metric

 2

Page 41: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

41Metric 1

Metric

 2Profile 1

Profile 2

Page 42: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

42

Page 43: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

43

Profile 1

Low EngagementHigh # At‐Risk

Low # Focused

Action Plan using Best Practices

Page 44: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

44

Measure Risk

Plan • Measure Risk• Action Plan

GroupingRankingTrendingAggregation

Page 45: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

45

Action Plan

Plan • Measure Risk• Action Plan

Action Plan

Page 46: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Expanding the Concept

Page 47: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

4747

Project Risk Recordable Body Part Cause

RFK Bridge 95% 41% Arm Struck By

National Harbor 80% 79% Back Slip/Trip

One Life Way 50% 15% Ankle Slip/Trip

Palo Construction 20% 2% Eye Foreign Object

OPD Headquarters 10% 1% Arm Laceration

Expanding the Concept

Page 48: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

4848

Project Risk Recordable Body Part Cause

RFK Bridge 95% 41% Arm Struck By

National Harbor 80% 79% Back Slip/Trip

One Life Way 50% 15% Ankle Slip/Trip

Palo Construction 20% 2% Eye Foreign Object

OPD Headquarters 10% 1% Arm Laceration

Future Capabilities

Page 49: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

4949

Future Capabilities

Project Risk Recordable Body Part Cause

Page 50: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

• People = data scientists and domain experts• Processes = collect and scrub data. Data quality.• Tools = many available• Adequate VSP• Engagement at all levels • Adequate plan to review/interpret results

– Data Use Plan– Seat at the Table 

50

Prerequisites for Success

Page 51: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

51

Page 52: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

52

ADVANCED MATH VERSUS BLACK BOX

Page 53: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Moving Away from Linear (Traditional) Models

Predict health given height and weight

Weight

Height

Healthy Individual

Unhealthy Individual

Page 54: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Moving Away from Linear (Traditional) Models

Predict health given height and weight

Weight

Height

Healthy Individual

Unhealthy Individual

Predict Healthy

Predict Unhealthy

Logistic Regression

Page 55: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Moving Away from Linear (Traditional) Models

Predict health given height and weight

Weight

Height

Healthy Individual

Unhealthy Individual

Predict Healthy

Predict Unhealthy

Logistic Regression

Page 56: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Moving Away from Linear (Traditional) Models

Predict health given height and weight

Weight

Height

Healthy Individual

Unhealthy Individual

Predict Unhealthy

Predict Unhealthy

Predict Healthy

Decision Tree

Page 57: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

• Leverage more of the data being captured

Traditional Approach Big Data Approach

Analyze small subsets of data Analyze all data

Analyzedinformation

All available information

All available informationanalyzed

Analytics can help identify “Useful” data

3

Page 58: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Slide 57

3 there's a point here about validating intuition AND finding new useful data, maybeAnn Gergen, 3/3/2015

Page 59: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Text Mining Variables

• Text mining refers to the process of deriving relevant and usable text that can be parsed and codified into a word or numerical value.

• Text mining can identify co‐morbid conditions and/situations that will have profound impact on the outcome of a claim.  

smoking

Pain unchanged

CXR

Diabetes/insulin/injections              Packs day/coughing Pain killers/anti‐depression   Children/school   Pain unchanged Height/Weight Homemaker wife went to work     c/o, CXR, FB, FX CBT – Cognitive Behavior Therapy

SAMPLE KEY WORDS/PHRASES

Text sources: Adjuster notes, medical reports, independent medical exams, etc.

Page 60: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Modeling Architecture 

Data Store – all historical data collected and organized

Training – identifying company/internal/external data specific patterns

Testing – using “hold out” sets to measure the accuracy of predictions

Page 61: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Segmentation Analysis - Tests Model Accuracy

Divide all scored claims into segments

● After scoring distribute by ranking risks by score

○ Highest Risk to the Right

○ Lowest Risk to the Left

○ Each claim has an individual score

○ Worst Claim far right vs. Best Claim far left

○ Then add actual losses to test model accuracy

Page 62: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Segmentation Analysis - Tests Model Accuracy

Divide all scored claims into segments

Lowest RiskBest Claims

Highest RiskWorst Claims

20% of scored claims 20% of scored claims 20% of scored claims 20% of scored claims 20% of scored claims

Page 63: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

High Risk

Low Risk

Early ID < Day 30 Models Identify 20% of Claims that have 78% of total costs

Medium Risk

Predictive Modeling in Action

2.19% 3.15% 4.74%

11.47%

4

Page 64: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Slide 62

4 early identification is most meaningful here! focus on how that translates to reserving, actuarial evals, etc.Ann Gergen, 3/3/2015

Page 65: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

63

APPLYING ADVANCED ANALYTICS TO UNDERWRITING

Page 66: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

GLM

Traditional Linear vs. Multivariate results

MULTIVARIATE

Page 67: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Daily Claim Alert Dashboard

Page 68: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine
Page 69: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

67

CASE LEVEL RESERVING DASHBOARDS

Page 70: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

Case‐Level Reserving Dashboard

Page 71: Predictive Analytics PA WC Conf June 2017 FINAL.pptx [Read ...€¦ · Predictive Analytics • Where: – Everywhere • Who: – Google – Uber – PeopleNet – Othot 10 “Machine

69