Risk Management Using Bayesian Networks and BayesiaLab - - PowerPoint PPT Presentation

▶
risk
SMART_READER_LITE
LIVE PREVIEW

Risk Management Using Bayesian Networks and BayesiaLab - - PowerPoint PPT Presentation

Nov 11, 2022 488 likes •988 views

The webinar will start at: 13:00:00 The current time is: 13:00:34 Central Standard Time UTC-6 Risk Management Using Bayesian Networks and BayesiaLab Introduction Your Hosts Today Stefan Conrady stefan.conrady@bayesia.us Stacey

slide-1
SLIDE 1

13:00:34

The current time is:

13:00:00

The webinar will start at: Central Standard Time UTC-6

Risk

Management

Using Bayesian Networks and BayesiaLab

slide-2
SLIDE 2

2 BayesiaLab.com

Your Hosts Today

  • Stefan Conrady

stefan.conrady@bayesia.us

  • Stacey Blodgett

stacey.blodgett@bayesia.us

Introduction

slide-3
SLIDE 3

3

Methodological Objective

  • Bayesian Networks for Managing Risk

Substantive Research Objective

  • Quantifying and mitigating the risk of

speeding violations in a transportation business context

Today’s Objectives

stefan.conrady@bayesia.us

“TOY PROBLEM”

slide-4
SLIDE 4

4

Motivation & Background
  • Regulations & Risk
  • Qualitative Risk Assessment
  • Risk Mitigation Proposal
Methodologies
  • Bayesian Networks for Reasoning Without Data
  • The Delphi Method
  • The Bayesia Expert Knowledge Elicitation Environment (BEKEE)
Software Demo
  • Building the Qualitative Structure
  • Eliciting Probabilities with BEKEE
  • Finding the Optimal Policy

Today’s Agenda

stefan.conrady@bayesia.us

40 min. 20 min.
slide-5
SLIDE 5

5 BayesiaLab.com

Teaching Edition Academic Edition BayesiaLab 6 Professional BayesiaLab WebSimulator Bayesia Expert Knowledge Elicitation Environment (BEKEE) Bayesia Engine API for Network Learning Bayesia Engine API for Modeling and Inference Code Export Module Bayesia Market Simulator

Web Application Desktop Software API

slide-6
SLIDE 6

6

Webinar Slides & Recording Available

stefan.conrady@bayesia.us

slide-7
SLIDE 7

7 BayesiaLab.com

Today’s Domain: Transport & Logistics

slide-8
SLIDE 8

8 BayesiaLab.com

Law

SPEED LIMIT

55

MINIMUM

55

Regulation Business Requirement

THE NEED FOR SPEED

Business

slide-9
SLIDE 9

9 BayesiaLab.com RISK

slide-10
SLIDE 10

10 BayesiaLab.com

Qualitative Risk Assessment

Risk Speed $ $$$

slide-11
SLIDE 11

11 BayesiaLab.com

slide-12
SLIDE 12

12 BayesiaLab.com

Premise

  • Human drivers are always at a risk of violating traffic rules, including speed limits.

Proposal for Risk Mitigation

  • Equip vehicle fleet with radar detectors to reduce the risk of speeding violations.

Note

  • We are only considering the risks of violating the law and its consequences, such
as a penalties, suspension of privileges, arrests, or vehicle seizures.
  • We are not looking at accident risks related to speeding, which of course exist.
  • We assume that radar detectors are legal for the purpose of this study, which is
not the case in many jurisdictions.

Risk Management

slide-13
SLIDE 13

13 BayesiaLab.com

Radar Detector

slide-14
SLIDE 14

14

SPEED KILLS

Note: We do not advocate speeding or the use of radar

  • detectors. Always obey all applicable traffic laws in your

jurisdiction.

slide-15
SLIDE 15

15 BayesiaLab.com

Study Questions

  • What is the base risk without radar detectors?
  • By how much do radar detectors reduce the risk of

speeding violations?

  • What is their expected economical value to an
  • rganization?
  • Do they potentially lead to unintended

consequences?

Risk Management

slide-16
SLIDE 16

16 stefan.conrady@bayesia.us

slide-17
SLIDE 17

17

But we only have observational data

stefan.conrady@bayesia.us

But what if we don’t have any data…

slide-18
SLIDE 18

18

“Without data, you’re just another person with an

  • pinion.”

No Data?

stefan.conrady@bayesia.us

  • W. Edwards Deming
slide-19
SLIDE 19

19 BayesiaLab.com

Argument

?

slide-20
SLIDE 20

20

Optimization Attribution Simulation Explanation Prediction Description

Model Purpose Model Source

Association/Correlation Causation Theory Data

Bayesian Networks to the Rescue!

BayesiaLab.com

slide-21
SLIDE 21

21

Optimization Attribution Simulation Explanation Prediction Description

Model Purpose Model Source

Association/Correlation Causation Theory Data

Bayesian Networks to the Rescue!

BayesiaLab.com

Reasoning Without Data

Even without data, humans do possess useful knowledge, qualitative or quantitative, tacit or explicit, about many aspects of the world.

slide-22
SLIDE 22

22

Optimization Attribution Simulation Explanation Prediction Description

Model Purpose Model Source

Association/Correlation Causation Theory Data

Bayesian Networks to the Rescue!

BayesiaLab.com

Reasoning Without Data

YELLOW CAB CO. WHITE CAB COMPANY

?

Webinar on March 2, 2018

slide-23
SLIDE 23

23 BayesiaLab.com

Reasoning Without Data

One Expert

Last Week

slide-24
SLIDE 24

24

Examples

  • Overconfidence
  • Confirmation bias
  • Framing effect
  • Escalation of commitment
  • Availability bias
  • Illusion of control
  • Anchoring bias

Knowledge Elicitation — Individual Biases

stefan.conrady@bayesia.us

slide-25
SLIDE 25

25 BayesiaLab.com

Reasoning Without Data

One Expert A Group of Experts

Last Week Today

slide-26
SLIDE 26

26

Examples

  • Groupthink (“toeing the line”)
  • Social loafing (“hiding in the

crowd”)

  • Group polarization (“taken to the

extreme”)

  • Escalation of commitment

(“throwing good money after bad”, “sunken costs fallacy”)

Knowledge Elicitation — Group Biases

stefan.conrady@bayesia.us

slide-27
SLIDE 27

27

Origins

  • The original Delphi method was developed in

the 1940s and 50s by Norman Dalkey of the RAND Corporation.

  • The Delphi method was devised in order to
  • btain the most reliable opinion consensus of

a group of experts by subjecting them to a series of questionnaires in depth interspersed with controlled opinion feedback.

The Delphi Method

stefan.conrady@bayesia.us

slide-28
SLIDE 28

28

Elicit Knowledge from Interacting Groups

  • Take the positive, e.g.
  • Knowledge from a variety of sources
  • Creative synthesis
  • Prevent the negative, e.g.
  • Groupthink (“toeing the line”)
  • Social loafing (“hiding in the crowd”)
  • Group polarization (“taken to the extreme”)

The Delphi Method

stefan.conrady@bayesia.us

slide-29
SLIDE 29

29

The Classical Delphi

  • Interviews via questionnaires
  • Anonymity of participants
  • Iteration
  • Controlled feedback
  • Statistical aggregation

The Delphi Method

stefan.conrady@bayesia.us

slide-30
SLIDE 30

30

“ to solicit expert opinion to th e selection, from th e point of view of a Soviet strategic planner,
  • f an optimal
U. S. indu strial target system. . . ”

First Experimental Application

stefan.conrady@bayesia.us

slide-31
SLIDE 31

31

“In view of the absence of a proper theoretical foundation and the consequent inevitability of having, to some extent, to rely on intuitive expertise—a situation which is still further compounded by its multidisciplinary characteristics—we are faced with two options: we can either throw up our hands in despair and wait until we have an adequate theory enabling us to deal with socioeconomic and political problems as confidently as we do with problems in physics and chemistry,
  • r we can make the most of an admittedly
unsatisfactory situation and try to obtain the relevant intuitive insights of experts and then use their judgments as systematically as possible.”

The Delphi Method

stefan.conrady@bayesia.us

slide-32
SLIDE 32

Utilizing Bayesian Networks with the Delphi Method

The Bayesia Expert Knowledge Elicitation Environment (BEKEE)

slide-33
SLIDE 33

33

  • 1. Brainstorming & Model Construction
  • Variables of interest
  • Causal relationships
  • Discretization levels
  • 2. Knowledge Elicitation (interactive/offline)
  • Facilitator posts assessment tasks
  • Participants submit assessments
  • 3. Inference & Optimization

BEKEE Workflow

stefan.conrady@bayesia.us BAYESIALAB BEKEE BAYESIALAB

slide-34
SLIDE 34

34

  • 1. Brainstorming & Model Construction

stefan.conrady@bayesia.us

Qualitative Network

Facilitator Experts

  • Variables of interest
  • Causal relationships
slide-35
SLIDE 35

35

  • 2. Knowledge Elicitation

stefan.conrady@bayesia.us BEKEE Server BAYESIALAB

Quantitative Elicitation

? ? ? ?

Facilitator Experts

Web Client

slide-36
SLIDE 36

36

Inference, Analysis, and Optimization

stefan.conrady@bayesia.us BAYESIALAB

Final Network

slide-37
SLIDE 37

37

Building the Bayesian Network Model

slide-38
SLIDE 38

38 BayesiaLab.com

Creating the Qualitative Structure

  • Variables (Nodes)

Knowledge Modeling

Qualitative Bayesian Network Structure from Brainstorming

slide-39
SLIDE 39

39 BayesiaLab.com

“Parameters” from BEKEE

slide-40
SLIDE 40

40

Inference & Optimization

slide-41
SLIDE 41

42

VR

In Conclusion…

slide-42
SLIDE 42

43 BayesiaLab.com

User Forum: bayesia.com/community

slide-43
SLIDE 43

44

bayesia.com/pricing-2018

BayesiaLab.com

slide-44
SLIDE 44

45

Try BayesiaLab Today!

  • Download Demo Version:

www.bayesialab.com/trial-download

  • Apply for Unrestricted Evaluation Version:

www.bayesialab.com/evaluation

BayesiaLab Trial

BayesiaLab.com

slide-45
SLIDE 45

46 stefan.conrady@bayesia.us

Upcoming Webinars:

  • March 16

Optimizing Health Policies with Bayesian Networks

  • March 23

t.b.d.

Register here: bayesia.com/events

Webinar Series: Friday at 1 p.m. (Central)

slide-46
SLIDE 46

47

  • April 11–13

Sydney, Australia

  • May 16–18

Seattle, WA

  • June 26–28

Boston, MA

  • July 23–25

San Francisco, CA

  • August 29–31

London, UK

  • September 26–28

New Delhi, India

  • October 29–31

Chicago, IL

  • December 4–6

New York, NY

BayesiaLab Courses Around the World in 2018

Learn More & Register: bayesia.com/events stefan.conrady@bayesia.us

slide-47
SLIDE 47

48 BayesiaLab.com

San Francisco

Introductory BayesiaLab Course in San Francisco, California July 23–25, 2018

slide-48
SLIDE 48

49 BayesiaLab.com

Chicago

6th Annual BayesiaLab Conference in Chicago November 1–2, 2018

slide-49
SLIDE 49

50

Thank You!

BayesiaLab.com

stefan.conrady@bayesia.us linkedin.com/in/stefanconrady facebook.com/bayesia BayesianNetwork