2022/03/14 by Jonas Crèvecoeur, Crevecoeur, Jonas, Katrien Antonio +5 · 2 citations
Decision Sciences · Economics, Econometrics and Finance · Social Sciences · #FOS: Economics and business #Insurance and Financial Risk Management #Insurance, Mortality, Demography, Risk Management #Probability and Risk Models #Risk Management (q-fin.RM)
paper · pdf · doi:10.48550/arxiv.2203.07145
openalex publication_date 2022/03/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Due to the presence of reporting and settlement delay, claim data sets\ncollected by non-life insurance companies are typically incomplete, facing\nright censored claim count and claim severity observations. Current practice in\nnon-life insurance pricing tackles these right censored data via a two-step\nprocedure. First, best estimates are computed for the number of claims that\noccurred in past exposure periods and the ultimate claim severities, using the\nincomplete, historical claim data. Second, pricing actuaries build predictive\nmodels to estimate technical, pure premiums for new contracts by treating these\nbest estimates as actual observed outcomes, hereby neglecting their inherent\nuncertainty. We propose an alternative approach that brings valuable insights\nfor both non-life pricing as well as reserving. As such we effectively bridge\nthese two key actuarial tasks that have traditionally been discussed in silos.\nHereto we develop a granular occurrence and development model for non-life\nclaims that tackles reserving and at the same time resolves the inconsistency\nin traditional pricing techniques between actual observations and imputed best\nestimates. We illustrate our proposed model on an insurance as well as a\nreinsurance portfolio. The advantages of our proposed strategy are most\ncompelling in the reinsurance illustration where large uncertainties in the\nbest estimates originate from long reporting and settlement delays, low claim\nfrequencies and heavy (even extreme) claim sizes.\n