Unbiased and Fair:

exam6addoil

• A model appropriately differentiates based on risk
• No systematic disadvantage to any protected group
• The ideal state for insurance pricing
• Off the top of my head I would think something where the insured is rated purely by telematics (i.e. only based on their driving habits) would be something that is 100% unbiased and fair

why it is unbiased here? it doesn't treat all customers identically, should it be biased??

exam6addoil

A model appropriately differentiates based on risk =>biased?

Staff-T1

"Bias in P&C pricing is any situation in which the outcomes of ratemaking models are
systematically less favourable to individuals within a particular group and where there
is no relevant difference between groups that justifies the difference in premiums or
rates"
This is from the paper. If a model appropriately differentiates between groups and the differentiation is justified then it is not biased

exam6addoil

If a model appropriately differentiates between groups and the differentiation is justified， would it be both unbiased and fair?

exam6addoil

okk, i am more confused now

“Biased but Fair:

A model charges different rates to groups defined by age
This is "biased" as it systematically differentiates
But if age correlates with accident risk, it may be actuarially justified
Society generally accepts age-based pricing as fair (where legal)”

so if it is systematically differentiates=>biased
if it is appropriately differentiates=>unbiased?

Staff-T1

Yes to both questions. I think the key point is that if you don't target any particular group systematically (ex young drivers, certain genders or skin colours) then you are not being biased, which is why if you price purely based on driving behavior you're not systematically targetting any particular group