An agregation method adapted to life insurance portfolios is presented. The aim of this work is to reduce the running time induced by the increasing complexity of actuarial models. The method is a two steps procedure. The first step consists in using statistical partitioning methods in order to gather insurance policies. The second step is the construc-tion of a representative policy for each aforementioned groups. Running times reduction techniques are motivated by the production in a timely manner of more and more sensitiv-ity analysis, required for both decision making and regulatory reporting. The efficiency of the agregation method is illustrated on a real saving contracts portfolio within the frame of a cash flows projection model used for best estimate liabilities and solvency capital re-quirements computations. The procedure is already part of AXA France valuation process.