D.W. Simpson Worldwide Actuarial Recruitment Life Health Pension Casualty US Asia Australia Europe Salary Apply Ezra Penland Actuarial Recruiters Top Actuary Jobs Salary Surveys Apply Bios Casualty Health Life Pension Pauline Reimer, ASA, MAAA Pryor AssociatesActuarial Openings: Life, P&C, Health, Pensions, Finance Advertise Here Contact us at actuary@actuary.com or 770-425-8576Reach top actuarial professionals

Thread: Risk calculus in insurance company

1. Risk calculus in insurance company

Hi there !
I'm studying programing and I have a lot of questions to ask.
I need to write a program that calculates the risk of current insurance product.
I don't know where should i start from.

Thanks for helping :embarrassed:

2. This is a really, really ambiguous question. The risk of an insurance product depends on a lot of things:

-- what type of product
-- the market(s) the product is sold in, and the state regulations involved
-- the volatility of the losses
-- the number of policies sold by the insurer(s)
-- the premium charged and the competitiveness of the market
-- the premium-to-surplus ratio of the insurer(s),
-- whether or not reinsurance is available [and the cost of it],
...

And so on and so forth. However, let's pretend this is personal auto in Easyvania where the state DOI doesn't have strict rules and insurers can write to whoever they want at whatever rate they want ... but, competition exists so they can't write \$5000 policies [because other insurers would obviously undercut them].

1. Decide on a distribution for an insured's loss, if he/she/it has one. Say, exponential with a mean of \$1500. [This could be gamma with mean \$1000 and variance \$500, ... your favorite distribution and favorite figures for mean and variance.]
2. Decide on a frequency for claims ... say, Poisson with mean 0.15
3. Decide how many insureds exist in Easyvania ... say, 100,000.
4. Now, model each insured and figure out (A) how many claims they have, and (B) what their losses are when they have a claim. [If they don't have a claim, their losses are obviously \$0.]
5. Determine the mean and variance of the losses.
6. Assume a premium-to-surplus ratio ... say, 2.5:1. [In other words, for every \$2.50 in premium there's \$1 in surplus available.]
7. Determine the premium such that there's a 1% chance of the insurer running out of money (running out of premium and surplus). Assume no expenses.

That should give you a lot of the setup; you should be able to expand and improve on things from here.