Terms of Reference:
|Accounting Earned Premium
This is the most common and widely understood method. The unearned premium reserve at the beginning of the period is added to the premium written (booked) during the period, and the unearned premium reserve at the end of the period is subtracted. Accounting Earned is the figure used in the Annual Statement.
This method calculates the premiums which were actually exposed to loss (or earned) for the period. The date on which premiums were booked is disregarded. What is significant is the effective date and term to which the premium applies. The portion of the premium written which was exposed to loss (earned) is allocated to the exposure period whether the premiums were booked prior to the period, during the period, or after the period. The exposure earned premium eliminates the deficiency contained in accounting earned premium that results from timing problems in the recording of premiums.
|Incurred But Not Reported (IBNR)
The liability for future payments on losses which have already occurred but have not yet been reported in the insurer’s records. This definition may be extended to include expected future development on claims already reported. Thus, technically IBNR covers the field from a) those individual losses that have occurred but have not been reported to the insurer to b) that amount of loss that may arise from a known loss which has been reported as an event but which has not been recorded in full to its ultimate loss value (known as loss development).
The process of changing the amount of estimated loss reserves as a policy or accident year matures, as measured by the difference between the paid losses and estimated outstanding losses at one point in time and the paid losses and estimated outstanding losses at some previous point in time. In common usage it might refer to development on reported cases only, whereas a broader definition would also take into account the IBNR claims.
Predictive (Modeling) analytics
Encompasses a variety of techniques from statistics, data mining and game theory that analyze current and historical facts to make predictions about future events.