RMI Lecture March 5

Outline of Expected Losses and Risk Management

I. Expected Losses

• Purpose: Estimate potential losses and prepare financially for unexpected events.

• Annual Forecasts: Serve as a baseline for risk managers to align strategies with operational outcomes.

• Data Requirements: Accurate measurements need a larger historical data set to identify trends.

A. Example

• Workers' Compensation Data: Analyze average injuries and costs to gauge financial losses related to employee accidents.

II. Measuring Risk

• Expected Vs. Actual Losses: Expected losses don't indicate the likelihood of varied outcomes.

• Standard Deviation: Measures variability; high standard deviation indicates uncertainty, low means closer to expected outcomes.

A. Key Question

• Effective risk management strategies consider risk tolerance levels for mitigation or transfer of risks.

III. Pooling and Diversification

• Pooling: Combines various risks to stabilize financial outcomes.

  • Single Stock Risk: Higher volatility and risk.

  • Diversified Portfolio: Stable returns, reduced uncertainty.

• Goal: Minimize losses and maximize return predictability.

IV. Risk Appetite and Maximum Probable Loss (MPL)

• Thresholds: Vary per company based on operational context.

• MPL Definition: Worst losses prepared for based on likelihood; aids in capital allocation planning.

• Preparation Strategy: Balance between capital allocation and safeguarding against risks.

V. Understanding Outcomes and Probabilities

• Key Calculation: Outcome - Expected Loss to quantify risks, especially in insurance.

VI. Central Limit Theorem and Law of Large Numbers

• Theorem: More observations lead to reliable expected loss estimates.

• Example: Expected loss of $875,000 with a standard deviation of $200,000 illustrates clustering toward the mean.

VII. Loss Predictions

• Preparation for Incidents: Expected loss of $875,000 suggests setting aside up to $1,275,000 for 95% of incidents to ensure financial stability.