: Insurance is a business of risk. Hence, risk analysis in insurance is very important. Insurance means insurance companies taking over
risks from customers. Level of risks determines insurance premiums. Insurers consider every available quantifiable factors to develop profiles of
high and low insurance risk. Insurances involving factors with greater risk of claims are charged at a higher rate. With much information at hand,
insurer can evaluate risk of insurance policies at much higher accuracy. However, advancement in the insurance industry has been hampered by
a lack of investment in data mining technology. In its absence, product designers are forced to work with limited detailed data about
policyholders and claim histories. Instead, they rely on data summarizations (actuarial tables summarize data), supplemented by intuitive
feelings to guide the development of new policy products, creative rating structures and appropriate premium charges. This paper presents a data
mining approach and its application to insurance risk analysis. Our model uses decision tree techniques to analyze risk levels into categories
(classes) based on past insurance claim history. The real dataset used contains information about policies and insurance claims on those policies.
Company can now use this information to adapt its premium policy.