ICFS-Plus: Actuarial Software for the Property and Causality Insurance Industry

ICRFS-ELRF™ 12

For your FREE copy of ICRFS-ELRF™ 12

Simply click here to email (ELRF@insureware.com). All you need to do is provide us with the following details:

1. Your Name
2. Company Name or University Name
3. Address
4. Telephone Number


Please note: Insureware Pty Ltd is committed to protecting your privacy. Personal/Professional information you provide to Insureware Pty Ltd will not be shared outside of Insureware Pty Ltd without your express permission.

 

Training videos are available for ICRFS-ELRF™ 12 along with FAQs


If you have any issues accessing the download, technical questions for installing or using the software, or wish to extend the free licence period, please contact Insureware.


A brochure on the Extended Link Ratio Family framework is available here.


Features and Benefits not available in other costly products!

ICRFS-ELRF™ 12 includes:

  • Full range of Link Ratio Techniques (LRT) models, with extensive link ratio selections (any size of diagonal with selection of average, weighted average, geometric average, maximum/minimum ratios etc).

LRT Ratio Selection Table


  • Two-parameter and three-parameter ratio smoothing, and final "to Ultimate" ratio, which can be computed as a product smoothed ratios at a given number of periods.
  • Regression formulation of all standard actuarial methods; this includes Mack and Murphy as special cases. Weighted average link ratios are formalised as regression estimators, with the further options of intercept and constant accident period trend for each development period. Standard deviations are computed analytically in all cases.

ELRF Templates


  • Projected Case Estimates, Payments Per Claim Incurred and Fisher-Lange methods.
  • Diagnostic statistics to test assumptions made by the model.

ELRF Weighted Residual Plot and FS - Mack


ELRF Weighted Residual Plot and FS - Murphy


  • Forecasts future calendar periods and calculates the standard errors of each year's forecast reserve.

ELRF Forecast Table


  • Calculate bootstrap sample distributions from link ratio models (no trend or intercept).

ELRF Bootstrap Table by accident year


  • Distributions from the ELRF bootstrap sample centered around the bootstrap mean (left) or model mean (right).

ELRF Bootstrap Simulations


Obtain sample distributions by accident year or calendar year - including VaRs and T-VaRs.


ELRF Bootstrap VaRs and TVaRs by calendar year


  • Forecasting by link ratio, Bornhuetter-Ferguson and Expected Loss Ratio.

ELRF Born-Ferg Table


  • Exposure and premium, letting you calculate loss ratios and exposure adjusted models.
  • Automated production of reports with Excel report templates including post processing of ICRFS-ELRF™ tables to create new tables.
  • A single database with example Triangle Groups of real loss development arrays.

For information about ICRFS-Plus™, click here.

For information about ICRFS-ELRF™ 12 Professional, click here.

For details of the differences between ICRFS-Plus™ 12, ICRFS-ELRF™ 12 Professional and ICRFS-ELRF™ 12, click here.


Database

An ICRFS-ELRF™ 12 database allows you to navigate effortlessly through your loss development arrays, models and reports with a few mouse clicks.


Link Ratio Techniques (LRT)

The link ratio techniques (LRT) module of ICRFS-ELRF™ 12 includes methods that are based on the standard average weighted link ratio techniques.


Extended Link Ratio Family (ELRF)

This module is an extension of the LRT module where average weighted link ratios are formalized as regression estimators through the origin, this incorporates the Mack method. These are extended to other modelling components of interest, including intercepts (the Murphy method) and a constant trend in the incrementals down the accident periods (for each development period). Resulting benefits include forecast standard error and testing that assumptions made by the model are supported by the data. Are there any features in the data not in the model and vice versa?


Now Insureware lets you:

  1. Test the claim that link ratio techniques lack predictive power and cannot capture volatility in the data.
  2. Read the Guide to Best Estimates.
  3. Use the models and techniques described in the ELRF section of the paper "Best Estimates for Reserves", previously on the CAS Syllabus of Examinations.
  4. Apply the bootstrap technique to any link ratio model (with delta = 0, 1, or 2).
  5. Text descriptions can be associated for any database object (datasets, models, etc) within triangle groups.
  6. Currency symbols are now respected.
  7. The bootstrap functionality for ELRF is extended to provide output similar to PALD (but based on bootstrap samples not parametric distributions). Distributions are available by accident year, calendar year, and total. Value-at-Risk and Tail-Value-at-Risk are also calculated. The sample can be shifted to the ELRF model mean or any user defined means by accident year. This module provides another diagnostic to determine whether link ratio methods are appropriate for the data.

 


 

See also for an overview on ICRFS-Plus™ 12 including the Probabilistic Trend Family (PTF) and Multiple Probabilistic Trend Family (MPTF) modelling frameworks.

 

"Extended Link Ratio Family (ELRF) models are the statistically derived and extended versions of the traditional actuarial Link Ratio Techniques (LRT), such as chain ladder. They provide more powerful modelling and enable statistical testing of the validity of the assumptions in the models. They almost invariably prove: "that in almost all real-world scenarios the data does not support those assumptions"


"I highly recommend "Best Estimates for Reserves" and hope that more of us will begin to use the methods that Barnett and Zehnwirth describe."


"Although the actuarial literature is replete with articles explaining the shortcomings of the traditional link ratio methods, most actuarial reserve analyses mainly rely on link ratio methods"


[Frederick Cripe, Chairperson, Casualty Accident Society (CAS), Research Policy and Management Committee.]