Description: The Society of Actuaries’ Committee on Finance Research is pleased to make available a research report that develops a framework for applying deep learning and reinforcement learning techniques to optimal dynamic strategic asset allocation for Liability Driven Investment (LDI).

Description: Description * This paper proposes a new type of financial derivative named contingent liquidity swap (CLS) to address the liquidity issue. CLS is a swap agreement that the buyer of the swap pays cash in exchange for less-liquid assets in the event of a liquidity event. Those less-liquid assets may include stocks or high-yield bonds. The seller of the CLS makes a series of payments for the contingent liquidity. The payment should be lower than the equity risk premium to reduce the cost of funding but high enough to attract investors.

Description: This article discusses how unemployment and underemployment information can help improve economic forecasts, insurance assumption setting and risk management. It summarizes the current modeling practices of unemployment which shows a deficiency of using unemployment/ underemployment information in actuarial works. It also gives three examples of using unemployment/underemployment information for economic assumption setting, new business growth prediction and stress scenarios related to the labor market.

Description: Wavelet models are used to analyze risk by time and frequency and provide richer information than time series models.

Description: With the credit interest rate floor of a cash balance plan—a simple type of option identified by the Project Oversight Group—as a model, this research uses three valuation and risk analysis approaches to explore the existing techniques to value embedded options on an economic basis.

Description: A primer on extreme event modeling and mitigation for practitioners, it covers the complete cycle of extreme event risk management, from identifying experience data sources, to extreme event detection, to modeling and dependence analysis, and finally to monitoring and mitigation.

Description: This article summarizes key points from the recently published research paper “Deep Learning for Liability-Driven Investment,” which applies reinforcement learning and deep learning techniques to liability-driven investment (LDI).

Description: This abstract describes a report that studies the social media response to three extreme tornado outbreaks in the Midwest United States.

Description: This article introduces a non-traditional type of economic scenario generator that relies on dynamic stochastic general equilibrium (DSGE) models are complex macroeconomics models and have been increasingly popular in central banks for analyzing monetary policies.

Description: The essay describes an application of “Do Jumps Matter in the Long Term? A Tale of Two Horizons,” by Jean-François Bégin and Mathieu Boudreault, published in the North American Actuarial Journal online Jan 5, 2021