Incorporating Liquidity Risk and Machine Learning within ERM and ALM to drive Risk-aware Business Decision-Making

This session takes a practical view related to the successful incorporation of Liquidity Risk and Machine Learning for Replicating Portfolios within ERM/ALM systems. While regulatory requirements are important considerations, the key drivers are to transform the business processes by providing actionable risk information to key business stakeholders. Participants will take away important lesson learned related to determining the appropriate implementation scope, data requirements and challenges, modeling choices and working across multiple departments and stakeholders to deliver tangible business benefits within a limited implementation timeframe. The handout will include functional architecture diagrams, modeling and methodology descriptions and examples of key deliverables to stakeholders.

  • Date:Monday, March 9
  • Time:2:35 PM - 3:50 PM
  • Location:Oasis I
  • Session Type:Concurrent Session
  • Session Code:CS15
  • Audience Level:2
  • Learning Objective 1::Make key technological and functional choices that allow your insurance firm to deploy a true ERM platform, which can address various business needs: from economic to regulatory capital, from asset and liability management to strategic asset allocation.
  • Learning Objective 2::Obtain a unified view of market, credit and liquidity risk to improve your portfolio construction process on the basis of a reliable correlation structure, without hindering the computational performance.
  • Learning Objective 3::Learn how Machine Learning techniques can be applied to create and automate the process for creating replicating portfolios for insurance liabilities for ERM and ALM purposes.
  • Moderator:David Core
Paolo Laureti
Algorithmics, Inc.
Andrew Dansereau
SS&C Algorithmics, Inc