Description: Artificial intelligence (AI) models have become increasingly popular in various industries, including finance. Such models can help lenders assess the risk of loan applicants, identify potential defaults and make better decisions about granting credit. However, the complexity of many machine-learning and, particularly, deep-learning models makes it difficult to understand how they arrive at their decisions. This lack of interpretability can be a significant problem in the legal and ethical realms, as it hinders transparency and accountability. Join us to learn interpretability techniques that are essential to address the challenges of using complex AI models in credit risk modeling. These techniques aim to provide a better understanding of how an AI model arrived at a particular decision or prediction. Techniques include surrogate models, which aim to provide a simpler model that approximates the behavior of the original model, and decision trees, which show the decision-making process in a more transparent way. However, applying interpretability techniques to AI models can be a challenging task. For example, some techniques can reduce the performance of the model, which can be unacceptable in applications where high accuracy is critical. Additionally, some techniques may only be effective for certain types of models or datasets, which limits their applicability. Despite these challenges, interpretability techniques are becoming increasingly important in the field of credit risk modeling. Financial regulators have recognized the importance of interpretability, and are starting to require financial institutions to use models that can be explained and validated. In addition, interpretability techniques can be used to improve the performance of credit risk models. By understanding how a model makes decisions, it is possible to identify areas where the model can be improved or where additional data may be needed.

Description: This webcast will walk through several statistical methods for imputing race and ethnicity from U.S. datasets, highlighting their strengths and weaknesses, talking about how to use them and evaluating their accuracy, and telling you where you can get code packages as well as a free dataset to try the methods out.

Description: Regression to the mean (RTTM) is inflating your health care intervention evaluations if you are not carefully managing it's omnipresent and significant impact RTTM is the statistical phenomenon which arises when comparing sequential data points when an initial observation is extreme or an outlier, and states that with no other intervention, future observations will be closer to the average. Members who had high costs last year will, on average, have lower costs this year, even in the absence of any intervention or clinical program, simply by 'regressing' to the mean. This means that if your clinical programs are simply targeting members who had adverse medical experience last year, you’re targeting the wrong people. And if your savings methodologies are simply last year’s costs minus this year’s costs, the savings are inflated. By attending this session, you will be able to identify situations where RTTM will be a significant factor, how to eliminate it's impact when performing retrospective evaluations, how to identify prospects for clinical intervention with RTTM in mind, and more.

Description: Dive into an overview of potential customer value propositions, trends in consumer acceptance and adoption, solving the data portability issue, potential impacts of emerging partner ships with OEMs and more within the auto insurance industry during our latest webcast. Experience interactive dialogue that will allow another dimension of thinking as industry experts provide insights and expertise. Throughout this webcast, you can expect developments in the personal lines automotive telematics-based insurance landscape that will develop a further understanding of the present and future of this industry.

Description: Have you ever struggled to make business decisions because your internal mortality studies lack credibility? Have you ever launched a new product or initiative and wanted to understand mortality risk before claims experience emerged? This session will discuss how predictive models can help actuaries enhance their traditional mortality studies with leading mortality leading indicators to be more nimble to market demands.

Description: CMS has required hospitals to publish their chargemaster rates, cash discounts and negotiated rates as of January 1, 2021. Our panel is comprised of a data strategist, an executive from a large hospital system and an actuary.

Description: Explore insights to non-traditional actuarial roles from a panelist with experiences in data science, finance and entertainment. The panelist will be sharing their perspectives on their non-traditional actuarial role in relation to the actuarial profession.

Description: This session will present the results of a case study investigating the impact of genetic testing on the reduction of health care costs. This will present both actuarial and clinical analysis of genetic testing in addition to researchers who are applying this approach.

Description: Volatile interest rates, repositioned investment portfolios, and stress in the banking sector are driving insurers to manage market risk and counterparty credit risk. Our experts in investments, derivatives, and hedge accounting will discuss this new market environment and its impact on hedging. The conversation will include practical case studies, including hedging future bond purchases, hedging floating-rate CLOs, and counterparty credit risk management.

Description: Reference Based Pricing (RBP) efforts have increased in popularity as tools to reduce the cost of care. Now with the ability to use CMS health plan transparency information, organizations can estimate the impact of savings from the use of RBP. This session will share the results of an analysis of this in the form of a case study.