Description: This chapter focuses on creating practical models that aid in the prediction of the risk of readmission to a specific hospital within 30 days of discharge for Medicare patients, to aid in the identification and stratification of at-risk patients for hospitals considering building an intervention program in a cost-effective manner. For readers who wish to develop their own predictive model, a dataset is provided on the Actexmadriver.com website, and R code is provided in the appendix to this chapter.

Description: The guest editorial details some valuable lessons during the author’s career as an employee benefits (mostly retirement) consultant, turned P&C predictive modeling, reporting and data warehousing lead, turned an analytic strategist and independent consultant.

Description: Research project that reviewed and inventoried the range of quality and efficiency measures that demonstrate the performance of hospitals and physicians. Besides outlining key areas of consideration for quality and efficiency measurement, this report also describes future opportunities for actuaries and other health professionals interested in this evolving area. The inventory part of this report is in a separate document.

Description: This research report addresses two purposes: [1] to incorporate phase transitions into a copula framework, and [2] to calculate the probability of defaulting in the context of a portfolio of correlated mortgages when a contagion effect exists. Understanding and measuring the effects that contagion has on the probability of defaulting, for both single assets and portfolios of assets, are crucial to collateralized debt obligation [CDO] markets.

Description: This paper shows how discrete multivariate analysis or multidimensional contingency table methods may be applied to data arising in actuarial work. A brief introduction to the theory is followed by two detailed examples of its application. Finally, the concluding remarks indicate how the procedure could be incorporated into a complete rate-making procedure. This work was performed for the U.S. Department of Housing and Urban Development.

Description: This paper deals with how the credibility levels change based on this lack knowledge. Group insuraace models are used, bill some of tile techniques could apply to any insurance risk.

Description: Presented at April 1986 Spring Meeting. This session discussion is about what analysis is effective in measuring recent medical care experience and are the projected cost-containment savings presented to plan sponsors being realized.

Description: Project portfolio risk management and risk analysis form one of the critical components of enterprise risk management. Organizations measure and analyze risks associated with projects, project portfolios, and programs. The important step of the process is quantitative risk analysis of project schedules using event chain methodology (ECM). ECM is a stochastic modeling technique for schedule risk analysis. All risks, including schedule and nonschedule-related risks, are assigned to a particular project and within this project to the particular activity or resource. Further, ECM allows one to model the relationship between project risks by defining risks that cause or trigger other risks. All risks and relationships between them will be presented on the project or portfolio Gantt charts using event chain diagrams. After risks are assigned to project and portfolio schedules, Monte Carlo simulation of the project schedule is performed. ECM simplifies complex risk analysis process.

Description: In order to better develop skill in predictive analytics, the author suggests looking to professionals who design innovative predictive models and, more importantly, find effective ways to communicate their findings to a large audience.

Description: Presented at May 1985 Spring Meeting. This session discussed: What measures should be used in setting objectives and evaluating performance for companies and product lines, What variations are appropriate for stock and mutual companies and for United States and Canadian companies.