Commercial Property Size of Loss Distributions Glenn Meyers Insurance Services Office, Inc. Casualty Actuaries in Reinsurance June 15, 2000 Boston, Massachusetts.

Slides:



Advertisements
Similar presentations
Introduction to Property & Casualty Actuarial Presenter: Matt Duke.
Advertisements

1 On Optimal Reinsurance Arrangement Yisheng Bu Liberty Mutual Group.
Increased Limits, Excess & Deductible Ratemaking Joseph M. Palmer, FCAS, MAAA, CPCU Assistant Vice President Increased Limits & Rating Plans Division Insurance.
Casualty Exposure Rating Chris Svendsgaard, Swiss Re Casualty Exposure Rating CARe Boot Camp
Unique Applications of Exposure Rating: Surety
Visual Recognition Tutorial
Systems of Index Numbers for International Price Comparisons Based on the Stochastic Approach Gholamreza Hajargasht D.S. Prasada Rao Centre for Efficiency.
Visual Recognition Tutorial
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 6-1 Chapter 6 The Normal Distribution and Other Continuous Distributions.
1 Math 479 / 568 Casualty Actuarial Mathematics Fall 2014 University of Illinois at Urbana-Champaign Professor Rick Gorvett Session 14: Credibility October.
Business Statistics: A First Course, 5e © 2009 Prentice-Hall, Inc. Chap 6-1 Chapter 6 The Normal Distribution Business Statistics: A First Course 5 th.
Introduction to Property Exposure Rating
GEN-3: Introduction to Increased Limits Factors
Introduction to Reinsurance Reserving Casualty Loss Reserve Seminar Washington, D.C. September 23, 2002 Bruce D. Fell, FCAS, MAAA Am-Re Consultants, Inc.
2008 Seminar on Reinsurance Reinsuring Commercial Umbrella Brian E. Johnson, ACAS, MAAA.
Risk Modeling of Multi-year, Multi-line Reinsurance Using Copulas
Reinsurance Structures and On Level Loss Ratios Reinsurance Boot Camp July 2005.
Permission to reprint or distribute any content from this presentation requires the prior written approval of Standard & Poor’s. Copyright (c) 2006 Standard.
The Cost of Financing Insurance Glenn Meyers Insurance Services Office Inc. CAS Ratemaking Seminar March 11, 2004.
Advancements in Territorial Ratemaking Allocating Cost of Catastrophe Exposure May 2006 CAS Spring Meeting Stephen Fiete.
Incorporating Catastrophe Models in Property Ratemaking Prop-8 Jeffrey F. McCarty, FCAS, MAAA State Farm Fire and Casualty Company 2000 Seminar on Ratemaking.
Generalized Minimum Bias Models
Copyright © 2008 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin 12 Financial and Cost- Volume-Profit Models.
Naive Bayes Classifier
Basic Ratemaking Workshop: Intro to Increased Limit Factors Jared Smollik FCAS, MAAA, CPCU Increased Limits & Rating Plans Division, ISO March 19, 2012.
Practical GLM Modeling of Deductibles
Bayesian Extension to the Language Model for Ad Hoc Information Retrieval Hugo Zaragoza, Djoerd Hiemstra, Michael Tipping Presented by Chen Yi-Ting.
Introduction to Exposure Rating CAS Ratemaking Seminar Boston March 17, 2008 Halina Smosna ACAS, MAAA Vice President, Endurance Re.
Casualty Excess Pricing Using Power Curves Ana Mata, PhD, ACAS CARe Seminar London, 15 September 2009 Mat β las Underwriting and Actuarial Consulting,
The Common Shock Model for Correlations Between Lines of Insurance
1999 CASUALTY LOSS RESERVE SEMINAR Intermediate Track II - Techniques
1999 CAS SEMINAR ON RATEMAKING OPRYLAND HOTEL CONVENTION CENTER MARCH 11-12, 1999 MIS-43 APPLICATIONS OF THE MIXED EXPONENTIAL DISTRIBUTION CLIVE L. KEATINGE.
The McGraw-Hill Companies, Inc. 2006McGraw-Hill/Irwin 12 Financial and Cost- Volume-Profit Models.
2004 CAS RATEMAKING SEMINAR INCORPORATING CATASTROPHE MODELS IN PROPERTY RATEMAKING (PL - 4) ROB CURRY, FCAS.
Reinsurance and Personal Umbrella Chuck Gegax FCAS Swiss Re CARe 2008.
Estimating the Predictive Distribution for Loss Reserve Models Glenn Meyers Casualty Loss Reserve Seminar September 12, 2006.
 2012 NCCI Holdings, Inc. WC-5 Just How Credible Is That Employer? Proposed Experience Rating Plan Changes CAS RPM Seminar Philadelphia, PA March 21,
2007 CAS Predictive Modeling Seminar Estimating Loss Costs at the Address Level Glenn Meyers ISO Innovative Analytics.
Premium Allocation for Blanket Rated Policies
On The Cost of Financing Catastrophe Insurance Presentation to the Casualty Actuarial Society Dynamic Financial Analysis Seminar By Glenn Meyers and John.
1 CMSC 671 Fall 2001 Class #25-26 – Tuesday, November 27 / Thursday, November 29.
© 2005 Towers Perrin March 10, 2005 Ann M. Conway, FCAS, MAAA Call 3 Ratemaking for Captives & Alternative Market Vehicles.
2004 CAS RATEMAKING SEMINAR INCORPORATING CATASTROPHE MODELS IN PROPERTY RATEMAKING (PL - 4) PRICING EARTHQUAKE INSURANCE DAVE BORDER, FCAS, MAAA.
On Predictive Modeling for Claim Severity Paper in Spring 2005 CAS Forum Glenn Meyers ISO Innovative Analytics Predictive Modeling Seminar September 19,
Glenn Meyers ISO Innovative Analytics 2007 CAS Annual Meeting Estimating Loss Cost at the Address Level.
1 - © ISO, Inc., 2008 London CARe Seminar: Trend – U.S. Trend Sources and Techniques, A Comparison to European Methods Beth Fitzgerald, FCAS, MAAA, CPCU.
Steve White, FCAS MAAA, Guy Carpenter Property Ratemaking - an Advanced Approach Exposure Rating June 6-7, 2005.
Chris Svendsgaard, FCAS, CPCU, MAAA Swiss Re
Property Exposure Rating Types of Exposure Rating Curves
Chapter 7 Financial Operations of Insurers. Copyright ©2014 Pearson Education, Inc. All rights reserved.7-2 Agenda Property and Casualty Insurers Life.
Practical GLM Analysis of Homeowners David Cummings State Farm Insurance Companies.
Logistic Regression Analysis Gerrit Rooks
Portfolio wide Catastrophe Modelling Practical Issues.
Kpmg 2002 Casualty Loss Reserve Seminar Surety Reserving Mike Rozema, ACAS, MAAA KPMG LLP.
Property Per-Risk Pricing Current Challenges David R. Clark American Re-Insurance Company CAS Seminar on Reinsurance; June, 2003.
Stochastic Loss Reserving with the Collective Risk Model Glenn Meyers ISO Innovative Analytics Casualty Loss Reserving Seminar September 18, 2008.
Increased Limits Ratemaking Joseph M. Palmer, FCAS, MAAA, CPCU Assistant Vice President Increased Limits & Rating Plans Division Insurance Services Office,
2000 SEMINAR ON REINSURANCE PITFALLS IN FITTING LOSS DISTRIBUTIONS CLIVE L. KEATINGE.
Paul Budde, Ph. D., ACAS, MAAA Senior Vice President Using Catastrophe Models for Pricing: The Florida Hurricane Catastrophe Fund CAS Special Interest.
1 Solving the Puzzle: The Hybrid Reinsurance Pricing Method John Buchanan CAS Ratemaking Seminar – REI 4 March 17, 2008 CAS RM 2008 – The Hybrid Reinsurance.
©Towers Perrin Introduction to Reinsurance Reserving Casualty Loss Reserve Seminar Atlanta, Georgia September 11, 2006 Christopher K. Bozman, FCAS, MAAA.
1 Casualty Actuarial Society Loss Reserve Seminar Chicago Marriott Chicago, Illinois ALLAN R. NEIS, FCAS, MAAA September 8-9, 2003 Closing the Books.
Naive Bayes Classifier. REVIEW: Bayesian Methods Our focus this lecture: – Learning and classification methods based on probability theory. Bayes theorem.
Reinsurance Insurers purchase reinsurance largely for the same reasons that people and organizations purchase insurance “Insurance for insurers” Functions.
2000 CAS RATEMAKING SEMINAR
Cost of Capital Issues April 16, 2002 John J. Kollar.
The Cost of Financing Insurance
Generally Discriminant Analysis
The Normal Distribution
Presentation transcript:

Commercial Property Size of Loss Distributions Glenn Meyers Insurance Services Office, Inc. Casualty Actuaries in Reinsurance June 15, 2000 Boston, Massachusetts

Outline Data Classification Strategy –Amount of Insurance –Occupancy Class Mixed Exponential Model –“Credibility” Considerations Limited Classification Information Program Demonstration Goodness of Fit Tests Comparison with Ludwig Tables

Separate Tables For Commercial Property (AY ) Sublines – BG1 (Fire and Lightning) – BG2 (Wind and Hail) – SCL (Special Causes of Loss) Coverages –Building –Contents –Building + Contents –Building + Contents + Time Element

Exposures Reported separately for building and contents losses Model is based on combined building and contents exposure –Even if time element losses are covered

Classification Strategy Amount of Insurance –Big buildings have larger losses –How much larger? Occupancy Class Group –Determined by data availability Not used –Construction Class –Protection Class

Potential Credibility Problems Over 600,000 Occurrences 59 AOI Groupings 21 Occupancy Groups The groups could be “grouped” but: –Boundary discontinuities –We have another approach

The Mixed Exponential Size of Loss Distribution i ’s vary by subline and coverage w i ’s vary by AOI and occupancy group in addition to subline and coverage

The Mixed Exponential Size of Loss Distribution i = mean of the ith exponential distribution For higher i ’s, a higher severity class will tend to have higher w i ’s.

The Fitting Strategy for each Subline/Coverage Fit a single mixed exponential model to all occurrences Choose the w i ’s and i ’s that maximize the likelihood of the model. Toss out the w i ’s but keep the i ’s The w i ’s will be determined by the AOI and the occupancy group.

Back to the Credibility Problem

Varying W i ’s by AOI Prior expectations Larger AOIs will tend to have higher losses In mixed exponential terminology, the AOI’s will tend to have higher w i ’s for the higher i ’s. How do we make this happen?

Solution Let W 1i ’s be the weights for a given AOI. Let W 2i ’s be the weights for a given higher AOI. Given the W 1i ’s, determine the W 2i ’s as follows.

Step 1 Choose 0  d 11  1 Shifting the weight from 1st exponential to the 2nd exponential increases the expected claim cost.

Step 2 Choose 0  d 12  1 Shifting the weight from 2nd exponential to the 3rd exponential increases the expected claim cost.

Step 3 and 4 Similar Step 5 — Choose 0  d 15  1 Shifting the weight from 5th exponential to the last exponential increases the expected claim cost.

Several AOI Groups Choose W’s for lowest AOI Group

Then choose d’s to Construct W’s for the 2nd AOI Group

Then choose d’s to Construct W’s for the 3rd AOI Group

Then choose d’s to Construct W’s for the 4th AOI Group

Continue choosing d’s and constructing W’s until the end.

Estimating W’s (for the 1st AOI Group) and d’s (for the rest) Let: F k (x) = CDF for kth AOI Group (x h+1, x h ) be the hth size of loss group n hk = number of occurrences for h and k Then the log-likelihood of data is given by:

Estimating W’s (for the 1st AOI Group) and d’s (for the rest) Choose W’s and d’s to maximize log- likelihood 59 AOI Groups 5 parameters per AOI Group 295 parameters! Too many!

Parameter Reduction Fit W’s for AOI=1, and d’s for AOI=10, 100, 1,000, 10,000, 100,000 and 1,000,000. Note AOI coded in 1,000’s The W’s are obtained by linear interpolation on log(AOI)’s The interpolated W’s go into the log- likelihood function. 35 parameters -- per occupancy group

On to Occupancy Groups Let W be a set of W’s that is used for all AOI amounts for an occupancy group. Let X be the occurrence size data for all AOI amounts for an occupancy group. Let L[ X|W ] be the likelihood of X given W i.e. the probability of X given W

There’s No Theorem Like Bayes’ Theorem Let be n parameter sets. Then, by Bayes’ Theorem:

Bayesian Results Applied to an AOI and Occupancy Group Let be the ith weight that W k assigns to the AOI/Occupancy Group. Then the w i ‘s for the AOI/Occupancy Group is:

What Does Bayes’ Theorem Give Us? Before –A time consuming search for parameters –Credibility problems If we can get suitable W k ’s we can reduce our search to n W ’s. If we can assign prior Pr{ W k }’s we can solve the credibility problem.

Finding Suitable W k ’s Select three Occupancy Class Group “Groups” For each “Group” –Fit W’s varying by AOI –Find W’s corresponding to scale change Scale factors from to by W k ’s for each Subline/Coverage

Graph of Log-Likelihoods

Prior Probabilities Set: Final formula becomes: Can base update prior on Pr{ W k | X }.

The Classification Data Availability Problem Focus on Reinsurance Treaties –Primary insurers report data in bulk to reinsurers –Property values in building size ranges –Some classification, state and deductible information Reinsurers can use ISO demographic information to estimate effect of unreported data.

Database Behind PSOLD 30,000+ records (for each coverage/line combination) containing: Severity model parameters Amount of insurance group –59 AOI groups Occupancy class group State Number of claims applicable to the record

Constructing a Size of Loss Distribution Consistent with Available Data Using ISO Demographic Data Select relevant data Selection criteria can include: –Occupancy Class Group(s) –Amount of Insurance Range(s) –State(s) Supply premium for each selection Each state has different occupancy/class demographics

Constructing a Size of Loss Distribution for a “Selection” Record output - Layer Average Severity Combine all records in selection: LAS Selection = Wt Average(LAS Records ) Use the record’s claim count as weights

Constructing a Size of Loss Distribution for a “Selection” Where:  i = ith overall weight parameter w ij = ith weight parameter for the jth record C j = Claim weight for the jth record

The Combined Size of Loss Distribution for Several “Selections” Claim Weights for a “selection” are proportional to Premium  Claim Severity LAS Combined = Wt Average(LAS Selection ) Using the “selection” total claim weights The definition of a “selection” is flexible

The Combined Size of Loss Distribution for Several “Selections” Calculate  i ’s for groups for which you have pure premium information. Calculate the average severity for jth group

The Combined Size of Loss Distribution for Several “Selections” Calculate the group claim weights Calculate the weights for the treaty size of loss distribution

The Deductible Problem The above discussion dealt with ground up coverage. Most property insurance is sold with a deductible –A lot of different deductibles We need a size of loss distribution net of deductibles

Size of Loss Distributions Net of Deductibles Remove losses below deductible Subtract deductible from loss amount Relative Frequency

Size of Loss Distributions Net of Deductibles Combine over all deductibles LAS Combined Post Deductible Equals Wt Average(LAS Specific Deductible ) Weights are the number of claims over each deductible.

Size of Loss Distributions Net of Deductibles For an exponential distribution: Net severity Need only adjust frequency -- i.e. w i ’s

Adjusting the w i ’s D j  jth deductible amount  ij W i

Goodness of Fit - Summary 16 Tables Fits ranged from good to very good Model LAS was not consistently over or under the empirical LAS for any table Model unlimited average severity –Over empirical 8 times –Under empirical 8 times

A Major Departure from Traditional Property Size of Loss Tabulations Tabulate by dollars of insured value Traditionally, property size of loss distributions have been tabulated by % of insured value.

Fitted $ Average Severity against Insured Value

Fitted Average Severity as % of Insured Value Blow up this area

Fitted Average Severity as % of Insured Value Eventually, assuming that loss distributions based on a percentage of AOI will produce layer costs that are too high.

PSOLD Demonstration No Information Size of Building Information Size + Class Information Size + Class + Location Information

Comparison with Ludwig Tables Tabulated by % of amount of insurance Organized by occupancy class and amount of insurance –Broader AOI classes –Broader occupancy classes Fewer occurrances No model A very good paper

Comparison with Ludwig Tables Ludwig — Exhibit 15 (all classes) Matched insured value ranges Obtained % of insured value distributions from PSOLD –assuming low end of range –assuming high end of range Results on Spreadsheet

What’s new for the next review? Include data through 1998 Fewer exclusions of loss information –Recall that we excluded claims if exposure and class information were missing. –Include claims if we trust the losses and use Bayesian techniques to spread losses to possible class and exposure groups. Include HPR classes