Description: View the Avoiding Unfair Bias in Insurance Applications of AI Models

Description: View the Data Challenges in Building a Facial Recognition Model and How to Mitigate Them

Description: PartnerRe Life and Health is rapidly growing its presence in global markets. This growth means that our medical underwriting team has to handle 25 percent more cases every year. To manage these additional cases without increasing headcount at the same pace, the team has to operate more and more efficiently. In a market where response time is a key differentiator, we improve efficiency by using machine learning to triage and prioritize the underwriting team's case work. In this talk, we describe the model pipeline end to end. That is, we cover the entire implementation chain from accessing data to the eventual evaluation of the added value. In particular, we discuss often neglected topics such as model risk mitigation, technical deployment of the model and integration into business processes.

Description: Our firm has developed the first publicly available insured lives mortality table for Cambodia using data science methods. This essay provides a brief background, our approach and the impact of our work.

Description: Neural Networks are no longer limited to classification and regression solutions to numeric problems. CNNs add the ability to classify images, and GANs can create new images. Learn how these capabilities can provide competitive advantages to early adopters, how they work, and how to implement them.

Description: There is enormous interest by investors and business leaders in the potential for artificial intelligence technologies, often powered by predictive modeling and machine learning, to transform the way that companies do business.

Description: Predictive modeling is a powerful toolset for assumption setting (mortality, lapse, etc.). The multivariate approach has its advantages in handling high-dimensional data, address correlations, and statistical significance. However, building insurance assumptions is far more than a simple modeling practice. One must take care to address how the model is applied and its business implications. This session will share the learnings from multiple projects.

Description: Ignite-style presentations feature presenters with 20 slides, automatically advancing every 15 seconds. The result is a fast and fun presentation which lasts just five minutes. The first portion of this session will feature insurtech innovators doing Ignite-style presentations on various insurtech topics. Then, stick around for the second portion when all presenters will take part in a moderated, talk show-style discussion. You'll get a chance to ask questions and dig deeper into the topics you just heard about. Find out how you can be part of the insurtech revolution. Be prepared for a fast-paced, thought-provoking session that you'll remember long after it ends!

Description: Artificial Intelligence (AI) is expected to change the insurance industry more in the next 10 years than it has changed in the past 100 years. Rapid advancements in computing power and the exponential growth of Big Data are creating more opportunities to incorporate AI techniques and methodologies into actuarial work. This session is for the practicing actuary who would like to learn more about AI and how to use it to analyze insurance data. At the conclusion of the session, attendees will be able to understand the fundamentals of AI, to build an AI model and to identify AI opportunities in their work.

Description: Natural Language Process (NLP) techniques can be used to find insights in large unstructured data sets and Word Embeddings are pervasive on a wide spectrum of NLP applications. These word representations improve downstream tasks such as Sentiment Analysis, Recommender System, and Topic Modeling. Learn how NLP transforms the Insurance Industry; and how word embeddings and pre-trained models improve the effectiveness and performance of NLP applications. NLP is increasing in importance for insurance companies. Additional application examples are available in session 36.