Description: Discussion of machine learning applications currently being used to augment traditional actuarial modeling in the life insurance industry. This includes data science techniques for: Quantifying and explaining differences between model versions or reporting periods Building proxy models for actuarial model output using machine learning One-class classification for data integrity checks Applications of unsupervised learning (e.g., clustering and principal components analysis) to reduce model run time

Description: In this video Jing Lang emphasizes the importance of ethical considerations in AI utilization, particularly focusing on privacy, bias, transparency, and creativity. It highlights the need for collaboration among various stakeholders to address these concerns through regulations, diversity promotion, and ongoing discussions. Sources of bias in AI, such as underrepresented datasets and historical biases, are identified along with strategies to mitigate bias, including careful assessment of inputs and retaining algorithms. Contributors: Jing Lang, FSA, FCIA, MAAA FLMI; Scott Allen, FSA, MAAAA, Henry Chen FSA, FCIA, MAAA; Jon Forster ASA, MAAA

Description: Yi-Ling Lin, FSA, MAAA, FCA, started the SOA’s Predictive Analytics Certificate Program to keep pace with the impact big data and predictive modeling is having on the health care industry

Description: Deep learning neural network applied to experience analysis for post-level term lapse and mortality.

Description: In recent years, vast amount of data from emerging experiences has helped insurers gain a deeper understanding of their policyholders and the factors driving their behaviors. However, due to limitations in traditional experience study methods, this understanding typically remains at the cohort level. This series of articles proposes a novel machine learning-based model that analyzes and predicts policyholder behaviors at the individual policy level. Policyholder embedding representations are learned using a Recurrent Neural Network (RNN) that takes into account the sequence of historical transactions associated with a policy. Additionally, a Neural Network with a multi-head architecture is trained to predict the policyholder's next action based on the policyholder embedding and other policy attributes. The resulting model offers several advantages over traditional experience studies and assumption-setting methods, including the ability to set policy-level assumptions that improve reserve accuracy, predict multiple behaviors simultaneously while capturing the interrelationships between them, and generate policyholder embedding representations that are useful for segmentation.

Description: Actuarial concepts of credibility can be extended to encompass additional information provided by new machine learning estimates. New statistical ideas also indicate how to generalize to blend arbitrarily many estimators, while not double-counting common information. For example, historical claim costs and risk scores both leverage diagnosis code information. We introduce two new estimators, one based on partial correlation and the other based on the machine learning-derived Shapley statistic, to address these limitations.

Description: "This video features Jing Lang, FSA, FCIA, MAAA , FLMI. Jing is an AI expert and Actuary with over 15 years working in the Insurance Industry. Here he provides an insightful overview of Artificial Intelligence (AI) and its various manifestations, from generative AI generating divers content to everyday applications like smart speakers and self-driving cars. It distinguishes between Artificial General Intelligence (AGI), which can perform tasks akin to humans, and Artificial Narrow Intelligence (ANI), which focuses on specific tasks.The narrative delves into key AI subfields like Machine Learning (ML), Deep Learning (DL), and Generative AI (GenAI), explaining their functionalities and differences.

Description: Generative AI is a frontier in artificial intelligence that can create new data from existing data sets, with applications in risk modeling, product development, data analysis, and more. This video presented by Chris Smith, ASA, MAAA introduces the fundamentals, technologies, and implications of generative AI for actuarial science, as well as the ethical considerations and limitations that actuaries must address. Learn how to harness the power of generative AI ethically and innovatively in your actuarial practice. Contributors: Chris Smith, ASA, MAAA; Jason Reed, FSA, MAAA; Sam Behrend, FSA, MAAA ; Jessica Calafell, FSA, MAAA; Jon Forster ASA, MAAA

Description: In this video, Joe Long ASA, MAAA, a consulting actuary and data scientist at Milliman, explains the concept of the bias-variance trade-off and its connection to actuarial credibility theory. He demonstrates how machine learning techniques like penalized regression can help actuaries balance bias and variance in their projections, using long-term care experience studies as an example. He also discusses the broader applicability and future directions of integrating advanced analytics into actuarial practice. Contributors: Joe Long ASA, MAAA; Jess Calafell, ASA, MAAA; Jon Forster ASA, MAAA

Description: We compare two predictive analytics methods - GLM and GBM in terms of predictiveness vs. interpretability.