Risk Management Process (DISC-327) SDSB-LUMS

Hubbard
Chapter 5
 The “Four Horsemen” of Risk Management – I

Actuaries
• Original professional risk managers
• Use a variety of scientific and mathematical methods
• Originally focused on assessing and managing the risks in insurance and pensions
• Branched out into other areas of risks as well

War Quants
• Engineers and scientists during World War II
• Used simulations and set up most decisions as a particular type of mathematical game
• Their descendants are users of probabilistic risk analysis, decision analysis, and
operations research
 The “Four Horsemen” of Risk Management – II

Economists
• After WWII, a new set of financial analysis tools were developed to assess and
manage risk and return of various instruments and portfolios
• Today, financial analysts of various sorts are the primary users of these methods
• Some overlap with the war quants

Management Consultants
• Most managers and their advisors use more intuitive approaches to risk management
that rely heavily on individual experience
• Developed detailed “methodologies” for these softer methods, especially after the
rising influence of managers addressing IT
• Users and developers of these methods are often business managers themselves or
nontechnical business analysts
• Auditors of various sorts (safety, accounting, etc.) included in this group because
certain influential methods they use have a common origin
 Gaps in Risk Management Practices among Different Groups

Actuaries and War Quants → Professional Engineers

• Consider the methods as entirely practical but unaware of systematic errors

Economists → Financial Analysts

• Vaguely aware of some of these solutions from other fields but not all of them

Management Consultants
• Usually not heard of some of the methods used by engineers or actuaries
• Consider other methods as impractical

Academic Researchers
• May have a research focus on any combination of the methods
• Not aware how well methods they research are used in the real world
 Actuaries – I

• Oldest profession in risk management

• Today’s insurance industry: an example of quantitative risk analysis

• Pre mid 1800s: ownership stake in an insurance company was more like gambling than investing
• Buying an insurance policy was no guarantee that the insurer would be financially able to cover losses
in a legitimate claim

• In days before general acceptance of (and legal requirement for) actuaries in insurance, quantitative
methods for assessing risk was a kind of competitive advantage

• Sweet spot to determine insurance premium: pay claims when a disaster occurred, don’t charge too much
to stay competitive, keep reserves at the expense of paying too few dividends to investors

• Credit Default Swaps (CDS)

• Case of AIG takeover by the US Government during the financial crisis of 2008-09
• A CDS is purchased by mortgage banks to offset the risk of borrowers defaulting on loans. Called as
swap in financial world because the parties both exchange cash but with different conditions and
payment schedules. In CDS, one party pays cash up front to the other in exchange for a future cash
payment on the condition that a borrower defaults on a loan.
 Actuaries – II

• Credit Default Swaps (CDS)

• Looks like insurance, sounds like insurance, feels like insurance—but, legally, it’s not regulated like
insurance
• The part of AIG’s business that actuaries did review was not the part that hurt the company

• When an actuary signs a statement claiming that an insurance company can meet its contingent liabilities
and is in a position to weather all but the rarest catastrophes, he or she puts his or her license to practice
on the line

• The name actuarial science aside, actuaries are not primarily trained to be scientists
• Most are more like engineers and accountants applying already-established methods
• Necessarily a conservative lot, the caution about adopting new ideas is understandable

• Post WWII: new and powerful methods are considered standard risk analysis by actuarial science

• Chartered Enterprise Risk Actuary (CERA) certification

• Purpose: extend the proven methods of actuarial science to topics outside of insurance.
• CERA-certified actuaries in enterprise risk management and operational risk management
 War Quants – I

• World War II changed Risk Analysis forever!

• Statistical Research Group (SRG) at Columbia University → Birth of Operations Research (OR)
• Estimating effectiveness of offensive operations and tactics that improved antisubmarine operations
• Earlier estimations: intelligence from monthly German tank production

• Manhattan Project → Monte Carlo simulation → A way to do math without exact numbers
• Problem: model fission reactions

• Rasmussen’s (MIT) Probabilistic risk analysis (PRA) as a basis for managing risks in nuclear power safety
• PRA used Monte Carlo models to simulate components of nuclear reactors and their interactions
• Probability of failures of each components of a complex system → Risk of failure of the entire system

• Von Neumann’s Game Theory → Mathematical description of games of all sort

• An important type of game: Player has no competitor but have to decide under uncertainty
• Implies nature as the other player: not rational, just unpredictable
• Real-world use-case: Invest in a new technology
• Outcomes: Investment may yield rewards or lost with nothing, or missed opportunity (if not invested)
 War Quants – II

• Types of one-person games against nature → Decision Theory & Decision Analysis
• Other applications: social welfare policy analysis, cold war nuclear strategies
• What the decision-makers should do + what they will do…

• Introduction of PCs: facilitation of Monte Carlo, Decisioneering & Palisade

• Culture of risk management for most engineers & scientists → Risk modeled quantitatively
• Analogy: reaction of an astrophysicist to theories proposed by an astrologer!

• Eager to improve models and remove weaknesses

 Economists – I

• Nobel Prizes in economics pre 1990s: explanations of macroeconomic phenomenon

• E.g. inflation, production levels, unemployment, money supply

• Modern Portfolio Theory (MPT) → Mathematical explanation

of Portfolio Diversification through Linear Programming
• Portfolio of investments has its own variance and return
• Changing proportion of investments, possible to generate
a variety of returns and volatility of returns
• Variability of the portfolio can be lower than that of a
single investment: due to independence
• Analogous to the uncertainty about the role of one
die, but far less uncertainty about the average of one
hundred rolls of dice
• Diversification together with the flexibility of setting the
proportion of each investment in the portfolio enables an
investor to optimize the portfolio for a given set of
preferences for risk versus return
• Issue of optimizing the choice of an individual making
decisions with risk was not previously part of economics
 Economists – II

• Black-Scholes Equation for Pricing Options: puts, calls, rights (not obligation) to buy or sell

• Empirical Observations
• Homo Economus: the economically rational human
• Behavioral Economics: how people actually do behave

• Difference b/w Economic Options Theory (OT) & MPT with PRA
• PRA: structural model, components of a system and their relationships modeled in Monte Carlo
• MPT and Black-Scholes equation: no explanation of underlying structure to price changes, various
outcomes are simply given probabilities, there is no way to compute the odds of a particular system-
level event such as a liquidity crisis if there is no history (unlike PRA)
• If nuclear engineers ran risk management this way, they would never be able to compute the odds of a
meltdown at a particular plant until several similar events occurred in the same reactor design

• Value at Risk (VaR): loss exceeded at a given probability

• A VaR is really just a single point on an LEC
• E.g. in a given portfolio of investment, the 5 percentile VaR is $10 million
 Economists – III

• Problems with OT, MPT and VaR

• They make some assumptions that do not match observed reality
• Major losses are far more common than these models predict
• Because they don’t attempt to model components of financial markets (e.g., individual banks, periodic
major bankruptcies, etc.) the way that a PRA might, these models may fail to account for known
interactions that produce common mode failures or cascade effects
• VaR can paint a very misleading picture of risk compared to the loss exceedance
 Management Consultants – I

• PowerPoint Thinking
• Deliverable: slides together with an oral presentation
• Heavy on graphics, light on content

• Random Deliverable Generator (RDG): actual content of the presentation didn’t matter as much as the
right combination of graphics and buzzwords

• Reliance on simple tools like Risk Matrix and Criticality Matrix: 3x3, 5x5 versions

• Failure modes, effects, and criticality analysis (FMECA)

• The most effective sales reps among the four horsemen

• Softest sell, the easiest sell, and the most successful sell of all the major risk management schools of
thought
• Unfortunately, they are also the most removed from the science of risk management and may have
done far more harm than good
Hubbard
Chapter 6
VOLATILITY VERSUS RISK
 Defining Risk Tolerance

• Risk Tolerance or Risk Appetite: how much risk an individual or organization is willing to endure

• Loss Exceedance Curve (LEC): Maximum bearable risk, independent of potential reward

• LEC to be entirely under Risk Tolerance Curve

• Would your firm pay $220,000 to avoid a 2% chance of losing $10M?

• Risk neutral person: No
• Risk is exactly equal to losing $200K for certain and would not pay more than that to avoid
the risk
• However, a firm would pay that if it was more like the typical insurance customer

• Certain Monetary Equivalent (CME): an exact and certain amount that someone would consider
equivalent to a bet with multiple uncertain outcomes
 Risk Tolerance: Certain Monetary Equivalent (CME)

• An exact and certain amount that someone would consider equivalent to a bet with multiple uncertain
outcomes

• An amount until you become indifferent between paying to avoid the risk or not

• Expressed as a negative value for losses: e.g. a payment of $250K to avoid a risk has a CME of −$250K

• CME for uncertain rewards:

• Example: choice between a 20% chance of winning $10M and a certain payment of $1M?
• Risk neutral → Uncertain reward value = $2M → prefers the uncertain gain over $1M certain payoff
• Some firms (and most individuals) would prefer the $1M certain amount
• Now, if the $1M cash in hand is preferred, perhaps an even lower certain amount would still be
acceptable to the uncertain amount
• Again, whatever the point of indifference for a given person or organization would be is the CME for
that uncertain reward → expressed as a positive amount (its a gain, not a loss)
• If CME is, say $300K, then you are indifferent between being paid $300K or taking your chances with
a 20% chance of winning $1M
CME = −S ∗ ln(1 − Utility ∗ Pr)
 Risk Tolerance: Utility

• Probability Weighted Utility: Perceived value from winning or losing

• Utility is nonlinear: most people don’t consider a 20% chance of winning $10M equivalent to $2M
• The first $2M may have a much bigger impact on a person’s life than the next $2M, and so on
• A person or organization’s utility function can describe CME for any set of uncertain outcomes.

• Exponential Utility Function Utility = 1 − exp(−X∕S)

• X: reward (−X is negative for a reward & positive for a loss) CME = −S ∗ ln(1 − Utility ∗ Pr)
• S: a scale unique to a individuals or organizations, defines risk
tolerance
• Pr: probability of a reward
• Produces a maximum utility of 1 no matter how much the
reward is
• For a smaller S, the decision-maker reaches “maximum utility”
with a smaller reward
• A loss, however, has a limitless negative utility
• Pleasure maxes out; pain does not
 Utility & CME: Examples

• Example 1: 20% chance of winning $10 million

• Assume a firm with an S of $5M
• Utility for the gain (from previous formula) = 0.8647
• CME (from previous formula) = $949,390
• => The firm is indifferent between a cash payment of $949,390 and a 20% chance of winning $10M

• Example 2: Individuals with a lower S will be indifferent with a much lower certain payoff
• CME = Indifference point between a certain amount and the uncertain reward
• If CME = $50K, S = $263,326 (much lower)

• Example 3: 2% chance of losing $10 million

• Assuming S = $5M
• Utility = -6.389
• CME = −$601,255
• If the company could pay $500K for insurance to avoid that risk entirely, it would pay it.
Measuring S: the scale unique to a given decision-maker or organization

Ron Howard proposed a kind of game to measure S:

• Imagine we play a game in which the outcome is based on a single coin flip. You could win
some amount of money x or lose half of x based on that flip. Would you take that bet?
• For example, you could win $200 if the coin flip lands on heads or lose $100 if it lands on
tails.
• A good bet if you assume you are going to play it a very large number of times. But suppose
you could only play it once.
• If so, how large would you be willing to make x so that the game is still just barely acceptable?
• We can use that as a measure of risk tolerance.
• For example, if you are willing to make x equal to $1000, then you would be willing to win
$1000 or lose $500 on a single coin flip.
• Howard shows how the largest number you would be willing to accept for x can actually be
used as a measure of S.
• Just like expected value, we can reduce risk to a single monetary value, except that we don’t
have to assume that a decision-maker is risk neutral
 Prospect Theory: Quantifying Real Risk Preferences – I

• Exponential Utility Function assumes that utilities are independent of previous wealth
• Preferences of individuals/firms for bets would remain same if they were billionaire or broke
• Likely a reason why risk preferences of individuals deviate from the exponential utility
function
• Example of gains:
• For S = $5M, the CME of a 20% chance of winning $50M is almost the same as that
of winning $500M or $5B.
• No matter how big the reward, the CME of a 20% chance of winning it never
exceeds $1,115,718 for a decision-maker.
• Example of losses:
• For large losses, the CME is surprisingly large for even tiny probabilities of a loss.
• The same decision-maker would pay almost $31M to avoid a one-in-a-million
chance of losing $100M

• Kahneman’s alternative approach to quantify real risk preferences: Prospect Theory

 Prospect Theory: Quantifying Real Risk Preferences – II

• Assume indifference among the three options in the table

• Executives may describe their risk tolerance by identifying three such bets as equally preferable
• No version of the earlier exponential function can make all three of these equally preferable
• Does that mean that the decision-maker is irrational?
• No, it just means that that a rational model is something other than that exponential function

• Model should cater for apparently irrational outcomes,

under unrealistic situations:
• E.g. investments larger than entire portfolio
• Nonsensical results (i.e., a decision-maker would
prefer investment A to B, B to C, and C to A)
• The spreadsheet gives options to calculate CME

• Influenced many areas of psychology and decision-

making – eventually winning the Nobel Prize in Economics
 Utility Models for Calculation of Risk Tolerance

• Constant Absolute Risk Aversion (CARA):

• CARA utility function is a measure of risk aversion
• It is characterized by a constant absolute risk aversion coefficient, meaning risk aversion is the same
for all levels of wealth
• This is usually unrealistic, as wealthy investors are less affected by financial losses

• Relative Risk Aversion (RRA):

• RRA measure represents the risk preferences of a decision-maker
• Depends on the outcome variable that is used as the argument of the utility function, and on the
way that outcome variable is defined or measured

• Exponential (Exp): Exponential Utility Function

Exp CME = Exp(Ln(Gain + Initial Wealth)*Pr Gain + Ln (Loss + Initial Wealth)*Prob Loss) – Initial Wealth
 Defining Probability from RM Perspective

• Probability: defined for truly random process, strictly repeatable, and used an infinite number of trials
• Never matches real world problems, e.g. kind of a cyberattack that has never happened before

• Aleatory Uncertainty: an ‘objective’ state of the system independent of our knowledge of it

• E.g. Known variability in a population of parts (looking at data, say 10% parts fail after 100 hours)

• Epistemic Uncertainty: Lack perfect knowledge about the objective facts

• Basis of most real-world decisions

• Calibrated Probability Assessments: experts providing subjective estimates can produce realistic
probabilities (with training and other adjustments)

• Risk is not just the product of probability and loss

• Multiplying them together unnecessarily presumes that the decision-maker is risk neutral
• Keep risk as a vector quantity in which probability and magnitude of loss are separate until we
compare it to the risk aversion of the decision-maker
 Summary of Terminologies – I

• Uncertainty: This includes all sorts of uncertainties, whether they are about negative or positive
outcomes. This also includes discrete values (such as whether there will be a labor strike during the
project) or continuous values (such as what the cost of the project could be if the project is between one
and six months behind schedule). Uncertainty can be measured (contrary to Knight’s use of the term) by
the assignment of probabilities to various outcomes. Although upside risk doesn’t make sense in our
terminology, the speaker can communicate the same idea by saying upside uncertainty.

• Strict Uncertainty: This is what many modern decision scientists would call Knight’s version of
uncertainty. Strict uncertainty is when the possible outcomes are identified but we have no probabilities
for each. For the reasons we already stated, this should never have to be the case.

• Probability: Probability is a quantitative expression of the state of uncertainty of the decision-maker (or
the expert the decision-maker is relying on). As such, a probability is always attainable for any situation.
The person providing the probability just has to be trained.
 Summary of Terminologies – II

• Risk Tolerance: Risk tolerance is described with a mathematically explicit calculation that can tell you if a
risk is acceptable. It could refer to the ‘maximum bearable’ risk, represented by a curve that the loss
exceedance curve should be under. It can also be a CME function that converts different uncertain
outcomes to a fixed dollar amount. A bet with a negative CME is undesirable (you would be willing to
pay, if necessary, to avoid the bet) and a bet with a positive CME is desirable (you would even pay more
for the opportunity to make the bet).

• Risk/Return Analysis: This considers the uncertain downside as well as the uncertain upside of the
investment. By explicitly acknowledging that this includes positive outcomes, we don’t have to muddy
the word risk by shoehorning positive outcomes into it. Part of risk/return analysis is also the
consideration of the risk aversion of the decision-maker, and we don’t have to assume the decision-
maker is risk neutral.

• Ignorance: This is worse than strict uncertainty because in the state of ignorance, we don’t even know
the possible outcomes, much less their probabilities. This is what former US Secretary of Defense Donald
Rumsfeld and others would have meant by the term unknown unknowns. In effect, most real-world risk
models must have some level of ignorance, but this is no showstopper toward better risk management.