Description: This presentation is a concurrent session from the 1991 Meeting of the Society of Actuaries, held April 18-19 in New Orleans. The panel will discuss the approaches and techniques used for pricing and modeling insurance products, including commercial software, internal systems, maintenance issues, staff training, and asset/liability systems. Discussion from participants is included. From the Record of Society of Actuaries, Volume 17, No. 1.

Description: Machine learning models have many practical applications in the world of insurance. These applications are well documented and most actuaries, at least at a high level, are familiar with these concepts. The presenters will take this one step further and provide an introduction to the theoretical formulas and real-world considerations that make machine learning models possible.

Description: This session will explore the practical aspects of bringing models to production, maintenance and management through its entire lifespan. Topics covered will include: production considerations, versioning, documentation, peer review and monitoring the model over its lifespan.

Description: As any international traveler who has tried to plug in an electronic device knows, the human race is great at devising many different ways to accomplish the same task. Predictive modeling is no different. Data scientists can choose from a wide variety of languages to prepare data, fit models, and verify results. The Rosetta Stone, which showed writing composed in three languages side by side, was instrumental in translating unfamiliar Egyptian hieroglyphics into the more common Greek language. This presentation follows a similar approach by showing the same predictive model implemented in the following languages: R, Python, Spark, MatLab, and SAS. Participants will compare and contrast each of these languages and, by doing so, build a greater understanding of those languages less familiar to them.

Description: 1999 SOA Annual Meeting, San Francisco. This panel analyzed the choices between purchasing actuarial software and developing the software in-house. Topics discussed: 1. Determination of software needs. 2. Evaluation of software packages. 3. Combining in-house developed software with commercial software. 4. Modifying commercial software to the needs of the organization. 5. Staffing and training for in-house developments versus staffing and training for installation of purchased software.

Description: Presented at October 1986 Annual Meeting. This session discussion is about the state-of-the-art in packaged software, the requirements of such systems, and current and future health care developments that must be addressed.

Description: Presented at May 1996 Spring Meeting. This session offers a retrospective and prospective look at the development of actuarial pricing models and technology tools.

Description: From a session at the 2000 Valuation Actuary Symposium held in Washington DC, September 14-15, 2000 Discussion of financial modeling considerations including: • Model platforms • Model structure • Static and dynamic model validation techniques • Data integrity

Description: Presented at May 1996 Spring Meeting. Discusses the new capabilities offered by Windows 95 from the perspectives of the end-user, software developer, and system administrator.

Description: Presented at September 1995 Valuation Actuary Symposium. This session talks about the Long-Term Care Insurance Valuation Task Force report.