Bias, Fairness, and the Modeling Lifecycle | Casualty Actuarial Society

Description

PLEASE NOTE: REGISTRATION WILL CLOSE 10 AM ET THE DAY OF THE WEBINAR. DUE TO HIGH VOLUME OF DEMAND, WE ARE ONLY ABLE TO GUARANTEE A SEAT TO THOSE WHO REGISTER 48 HOURS AHEAD OF THE WEBINAR TIME.

In this session, we will describe one insurer's experience with integrating bias and fairness considerations into its predictive modelling plans. Our objective is to educate the audience on the practical considerations of operationalizing the bias and fairness concepts that have been the subject of presentations and research papers by the CAS and other organizations. We are members of a Working Group that has been spearheading efforts to increase adoption of bias and fairness checks by our company's predictive modelling teams. We will share some practices to achieve this goal and demonstrate their use through a case study. Examples of these practices include developing qualitative guidance on when and how to incorporate fairness considerations into a modelling project plan, ensuring that analysts have access to guidance to assist with selecting technical methodologies for detecting bias, and developing supplementary in-house content to facilitate adoption of these tests throughout the model lifecycle.

Learning Objectives:

1. Modify a predictive modeling project plan to ensure that bias and fairness are considered at all stages of the model lifecycle.
2. Recommend approaches to selecting relevant bias detection tests for a predictive model.
3. Develop a plan to address barriers to adoption of bias and fairness checks.

Registration Information and Fees

PLEASE NOTE: REGISTRATION WILL CLOSE 10 AM ET THE DAY OF THE WEBINAR

Registration Fees (in U.S. Dollars)	Received on/by April 30, 2024	Received after April 30, 2024
Individual	$50	$75
Multiple Connections** (Unlimited internet connections for individuals working for the same company. Please note that audio for this presentation will be streamed via the web)	$600	$650

*Multiple Connection Registrations should contact Mallory Peebles directly at mpeebles@casact.org. The registering party for the Multiple Connection Registration will be responsible for distributing all event details to attending individuals within their company.

No Broadcast Policy
Your registration entitles you to access CAS’ webinar programs for which you have registered. By registering to attend the webinars, you agree not to sell, transfer, or otherwise share your webinar access link and/or code unless such sharing is authorized by CAS. You further agree not to record or broadcast CAS’ webinar programs without advance written authorization by CAS.

Cancellations/Refunds
Registrations fees will be refunded for cancellations received in writing through email, refund@casact.org, by May 7, 2024 less a $25 processing fee.

CAS Continuing Education Policy
The CAS Continuing Education Policy applies to all ACAS and FCAS members who provide Actuarial Services. Actuarial Services are defined in the CAS Code of Professional Conduct as “professional services provided to a Principal by an individual acting in the capacity of an actuary. Such services include the rendering of advice, recommendations, findings or opinions based upon actuarial considerations.” Members who are or could be subject to the continuing education requirements of a national actuarial organization can meet the requirements of the CAS Continuing Education Policy by satisfying the continuing education requirements established by a national actuarial organization recognized by the Policy. For further information regarding the CAS Continuing Education Policy please visit the CAS web site.

CAS Webinars may qualify for up to 1.8* CE Credits for CAS members. Participants should claim credit commensurate with the extent of their participation in the activity. CAS members earn 1 CE Credit per 50 minutes of educational session time, not to include breaks and/or lunch. *The amount of CE credit that can be earned for participating in this activity must be assessed by the individual attendee. It also may be different for individuals who are subject to the requirements of organizations other than the Casualty Actuarial Society.

Contributors

Elizabeth (Liz) Bellefleur-MacCaul

Elizabeth (Liz) Bellefleur-MacCaul is currently a Senior Actuarial Analyst at Definity. Formerly based out of Montreal, Quebec, Liz joined Definity (formerly known as Economical Insurance) in 2018 before relocating to Ottawa, Ontario. Having spent most of her career within Definity's Personal Insurance department, Liz's primary responsibility has been the development of predictive models for pricing personal automobile and property products. More recently, she has joined the Advanced Analytics business unit, where she's responsible for both personal and commercial lines analytics solutions outside of the scope of traditional pricing models.

Since its inception, Liz has been an active member of Definity's cross-functional working group for addressing the impact of bias and fairness in predictive modelling and analytics. The working group's progress towards operationalizing bias and fairness considerations across the organization was recognized in 2023 when they were shortlisted as finalists for Definity's CEO Award.

Throughout 2023, Liz held the role of Vice-Chair of the company-wide Women's Empowerment Employee Group, one of several employee groups at Definity committed to fostering and championing Inclusion, Diversity, Equity & Accessibility (IDEA) in the workplace. As of January, Liz has been selected as the inaugural Chair of Definity's Disability & Accessibility Advocacy Employee Group, and will be leading the efforts to build this newly formed group from the ground up. As a community member herself, Liz envisions a workplace where disability is embraced as an integral part of diversity, such that employees of all abilities can bring their authentic selves to work and thrive.
Craig Sloss

Craig Sloss is a Technical Consultant and Lead Data Scientist at Definity Financial Corporation, the sixth-largest Property-Casualty insurer in Canada, headquartered in Waterloo, Ontario. Craig obtained his PhD in Combinatorics and Optimization from the University of Waterloo in 2011, and is a Fellow of both the Casualty Actuarial Society and the Canadian Institute of Actuaries. He worked as a lecturer in mathematics at Wilfrid Laurier University prior to joining Definity's predecessor company, Economical Insurance, in 2014. He still occasionally teaches a course in predictive analytics at the University of Waterloo. As a member of Definity's Advanced Analytics team, he provides technical guidance and support to team members working on using predictive models to find solutions to business problems for functions such as claims management, underwriting, and fraud detection. He also coordinates Definity's "Bias and Fairness Working Subcommittee," a group consisting of representatives from departments having an analytics component, including Pricing, Corporate Actuarial, Customer Insights and Advanced Analytics. This group's mandate is to facilitate the adoption, across the various analytics teams, of techniques to measure bias and assess fairness of customer-impacting models. This is done through a combination of operationalizing external research, such as the CAS Research Paper Series on Race and Insurance Pricing, and developing internal best practices and procedures for performing bias and fairness assessments. Outside of work, Craig is active in local politics, with a focus on advocating for better use of data by municipal governments. In his spare time, you can usually find Craig at a local cultural event, and he's a big fan of the music scene in the Kitchener-Waterloo area.

Description

Contributors

Elizabeth (Liz) Bellefleur-MacCaul

Craig Sloss