1 / 39

METODOLOG ÍAS Y PRÁCTICAS EN RESERVAS TÉCNICAS PARA SEGUROS DE SALUD Y SEGUROS GENERALES LIMA – 31 DE MAYO, 2007 APESE

METODOLOG ÍAS Y PRÁCTICAS EN RESERVAS TÉCNICAS PARA SEGUROS DE SALUD Y SEGUROS GENERALES LIMA – 31 DE MAYO, 2007 APESEG Presentado por: APESEG & Milliman, Inc. ■ Basic Methods for Evaluating Reserves ■. LOSS RESERVING METHODS. In practice, many methods estimate “Ultimate Losses”

kobe
Download Presentation

METODOLOG ÍAS Y PRÁCTICAS EN RESERVAS TÉCNICAS PARA SEGUROS DE SALUD Y SEGUROS GENERALES LIMA – 31 DE MAYO, 2007 APESE

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. METODOLOGÍAS Y PRÁCTICAS EN RESERVAS TÉCNICAS PARA SEGUROS DE SALUD Y SEGUROS GENERALES LIMA – 31 DE MAYO, 2007 APESEG Presentado por: APESEG & Milliman, Inc. ■ Basic Methods for Evaluating Reserves■

  2. LOSS RESERVING METHODS • In practice, many methods estimate “Ultimate Losses” • Loss Reserves are Obtained By Subtraction Estimated Ultimate Losses Paid to date Losses Total Reserve - = IBNR Reserve Total Reserve Case Reserve = -

  3. LOSS RESERVING METHODS • Expected Loss (Loss Ratio) • Loss Development (Chain Ladder) • Tail Factors • Inflation Adjustments • Bornhuetter-Ferguson • Generalized Cape Cod • Many, many others available

  4. BASIC METHODS – BASEBALL EXAMPLE • Given the following information, how many homeruns will Sammy Sosa finish with in the 2007 season? • 2004 total homeruns: 40 • 2005 total homeruns: 35 • 2006 total homeruns: 45 • 2007: 20 homeruns through 40 games of the 160 game season

  5. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season?

  6. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season? • Based on the prior 3 years, the Expected Value would be 40 homeruns.

  7. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season?

  8. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season?

  9. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season? • What is the Bornhuetter-Ferguson (B-F) Method? • Named after paper written by Ron Bornhuetter and Ron Ferguson published in the Casualty Actuarial Society Proceedings 1972. • Compromise between the Expected Loss and Loss Development Methods.

  10. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season? • What data is needed for the B-F Method? • Expected Ultimate Value (40) • Factor to Project Actual Data to Ultimate (4.000) • Actual Data to Date (20)

  11. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season? B-F Projection: Ultimate Value = (Expected Value*IBNR Factor)+(Inc. to Date) • IBNR Factor = 1.000 - (1.000/LDF) = 1.000 - (1.000/4.000) = .75 (In Other Words, 75% of the season is left to be played) • Ultimate Value = (40 * .75) + 20 = 50

  12. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season? Expected Value Method Games 0-40 Games 41-80 Games 81-120 Games 121-160 10 Home Runs 10 Home Runs 10 Home Runs 10 Home Runs Development Projection Method Games 0-40 Games 41-80 Games 81-120 Games 121-160 20 Home Runs 20 Home Runs 20 Home Runs 20 Home Runs Bornhuetter-Ferguson Method Games 0-40 Games 41-80 Games 81-120 Games 121-160 20 Home Runs10 Home Runs 10 Home Runs 10 Home Runs

  13. BASIC METHODS – BASEBALL EXAMPLE • How many homeruns will Sammy Sosa finish with in the 2007 season?

  14. BASIC METHODS – BASEBALL EXAMPLE • Comparison of Methods If Actual 10 After 40 Games If Actual 5 After 40 Games If Actual 20 After 40 Games

  15. LOSS RESERVING METHODS • Each Method is Based on Idealized Model of Reality • Models have Implicit Assumptions • Such Assumptions are Rarely Satisfied • No single method or “Formula” will work • Use multiple methods • Use judgment in selecting values • Actuary to test Assumptions • Review Diagnostics • Possibly Use Additional Methods to “Adjust” Data

  16. LOSS RATIO METHODS Expected Loss Ratio E(LR) Earned Premium Ultimate Losses x = • Problem. I know the earned premium, but how do I estimate the Expected Loss Ratio? • Use Pricing Assumptions • Use Available Industry Information • Useful when Company does not have relevant information to analyze • New Business • Small Volume • Late Reporting of Losses (e.g., high excess of loss).

  17. EXPECTED LOSS RATIO METHOD

  18. EXPECTED LOSS METHOD EXAMPLE

  19. DEVELOPMENT METHOD • Also Called the Chain Ladder Method and the Completion Factor Method • Data Triangles • Paid Loss • Incurred Loss • Claim Counts

  20. TRIANGLE EXAMPLE

  21. TRIANGLE EXAMPLE

  22. LOSS DEVELOPMENT METHOD EXAMPLE

  23. “TAIL” FACTORS • Previous Example Showed Development to 60 Months • Suppose Process is Not Complete • Curve Fits • Industry Information • Paid to Incurred Ratios • Judgment

  24. LOSS DEVELOPMENT METHOD EXAMPLE

  25. LOSS DEVELOPMENT METHOD EXAMPLE

  26. IMPORTANCE OF “TAIL” FACTOR

  27. IMPORTANCE OF “TAIL” FACTOR

  28. PAYMENT/REPORTING PATTERNS

  29. EXAMPLE PAYMENT PATTERNS

  30. EMERGENCE AND SETTLEMENT PATTERNS

  31. BRINGING RESULTS TOGETHER • Make Tentative Selections • Loss Development Factors • Tail Factors • Expected Loss Ratios • Generalized Cape Cod Trend and Decay • Weights for Various Methods

  32. BRINGING RESULTS TOGETHER

  33. BRINGING RESULTS TOGETHER

  34. BRINGING RESULTS TOGETHER • Check Ultimate Losses for Reasonableness by Reviewing additional Diagnostics • Ultimate Loss Ratios • Frequency and Severity • Percent of Total Loss by Year • Paid, Case Reserve, IBNR • Ratios of Ceded Reserves to Total Reserves • Average Hindsight Outstanding Cost Per Open Claim • Many Others • Sensitivity Test • Reasonable Ranges for Key Selections

  35. BRINGING RESULTS TOGETHER

  36. BRINGING RESULTS TOGETHER

  37. BRINGING RESULTS TOGETHER

  38. BRINGING RESULTS TOGETHER

  39. BASIC METHODS REVIEW • Basic Methods • Expected Loss • Loss Development • Bornhuetter-Ferguson • Cape Cod • Reasonability and Sensitivity of Estimates • Tail Factor Selection • Review of resulting Ultimate Loss Ratios, Claim Severities and Frequencies, and other Diagnostics • Sensitivity of Results to Key Assumptions • Loss Adjustment Expenses • Documentation

More Related