Chock full of thought leadership, CAS research attracts tens of thousands of website visits annually. The year 2024 was no exception. Researchers explored a wide range of topics, offering innovative ideas on subjects ranging from artificial intelligence to social inflation. CAS research presented fresh thinking on actuarial fundamentals while introducing new techniques.
This top 10 list showcases the most visited CAS research literature during calendar year 2024, featuring enduring topics of interest while revealing research that stands the test of time. Most papers touch upon modeling for reserving and rating as well as capital assessments and marketing. Sprinkled within these papers are applications for deploying machine learning, gleaning insight from textual data and determining liability for autonomous vehicles.
Top 10 Most Popular CAS Research of 2024:
#1 Loss Modelling from First Principles Pietro Parodi, Derek Thrumble, Peter Watson, et. al. CAS E-Forum, 2024
About: The authors establish a first principles approach that reshapes loss modeling and enhances clarity, precision and predictive power. This methodology balances fitting data with dynamic risk while avoiding complex, parameter-heavy methods in favor of intuition and mathematics.
Why Read? Modeling with first principles can still be the best approach.
#2 GLM for Dummies (and Actuaries) David R. Clark, CAS E-Forum, 2023
Offering insights to support robust, interpretable and adaptable ratemaking models, this paper addresses common modeling challenges such as data sparsity, regulatory requirements and real-world variability. By calculating a fitted model so the weighted average of the fitted loss costs balances to the actual data, the paper strives to make the heart of calculation more intuitive.
Why Read? Learn what anyone (including actuaries) would want to know about GLMs – but were afraid to ask.
#3 Machine Learning and Ratemaking: Assessing Performance of Four Popular Algorithms for Modeling Auto Insurance Pure Premium Sofia Colella, Harrison Jones, CAS E-Forum, 2023
By integrating evolving modern machine learning ratemaking techniques, such as XGBoost and neural networks, the authors strive to give actuaries the competitive advantage that GLMs can provide. While providing actionable insights on turning and performance, the paper can also help readers understand the trade-offs between accuracy and interpretability.
Why Read? Machine learning is powerful, but there’s always nuance.
#4 A Simple Method for Modeling Changes over Time Uri Korn, Variance, August 3, 2021
The author introduces a regression-based state-space model (RSSM) that significantly improves time series forecasting in reserving. By combining penalized regression with time series elements, the paper enhances the interpretation of historical data and boosts forecasting accuracy. Practical applications span reserving, profitability analysis and insurance pricing, with a focus on scalable solutions for big data.
Why Read? There is an innovative approach to time series forecasting.
#5 Ultimate Loss Reserve Forecasting Using Bidirectional LSTMs Lahiru H. Somarantne, CAS E-Forum, 2022
By introducing models like recurrent neural networks (RNN) and long short-term memory (LSTM), the author reveals how machine learning can handle temporal components of loss data effectively, surpassing traditional methods such as chain ladder in accuracy, especially for volatile early loss development periods.
Why Read? Address age-old challenges by leveraging machine learning in predictive loss reserving.
#6 Framework of BERT-Based NLP Models for Frequency and Severity in Insurance Claims Shuzhe Xu, Vajira Manathunga, Don Hong, Variance, 2023
This paper introduces a cutting-edge framework for utilizing textual data in insurance datasets through bidirectional encoder representations from transformers (BERT)-based natural language processing (NLP). By combining BERT with artificial neural networks, the authors demonstrate significant improvements in predictive accuracy and stability for modeling claim frequency and severity, outperforming traditional methods.
Why Read? Incorporating text data in complex models is made possible with a practical, powerful procedure.
#7 Capital Allocation Techniques: Review and Comparison Qiheng Guo, Daniel Bauer, George H. Zanjani, Variance, 2021
Bridging theory and practice, the authors provide a critical review of capital allocation methods, exploring their underpinnings, practical implementations and stability through examples. This sought-after paper also identifies key differences between methods, tail-focused measures and those considering entire distributions covering the instability of methods such as Value-at-Risk (VaR) under certain conditions.
Why Read? The C-Suite will always appreciate capital allocation with more robust metrics for portfolio optimization and risk-adjusted return.
#8 Recommender Systems for Insurance Marketing Giorgio Alfredo, Giuseppe Savino, Variance 2022
Just as e-commerce and entertainment industries use state-of-the-art recommender systems (RSs) algorithms to market their businesses, so can insurance companies — with help from actuaries. The authors show how supervised learning models, such as gradient boosting and neural networks, can better predict insurance purchases compared to traditional techniques. As a bonus, the paper also shares insights to enhance cross-selling strategies, improve customer engagement and drive business growth.
Why Read? It never hurts to gain appreciation from the marketing department.
#9 A Practical Approach to Quantitative Model Risk Assessment Carole Bernard, Rodrigue Kazzi, Steven Vanduffel, Variance, 2023
The authors present a practical framework for assessing quantitative model risks, emphasizing the impact of model assumptions. They introduce innovative tools to evaluate assumption contributions to overall risk and provide a formula for calculating model risk capital. The research also addresses regulatory requirements and offers strategies to improve model reliability.
Why Read? Evaluating, mitigating and communicating model risks can bolster better financial decision making.
#10 Projection of On-Road Liability Losses for Autonomous Driving Tetteh Otuteye, Corey Rousseau, Rafael Costa, et al. CAS E-Forum, 2022
Combining actuarial expertise with advancements in autonomous vehicle (AV) technology and safety systems, this paper explores evolving challenges in liability assessment. The authors provide methodologies to project risks, price coverage, and anticipate reserves by addressing critical factors such as liability exposure quantification, collision frequency, claim severity, and loss distribution. Additionally, the research examines the interplay of product and personal liability, variations in regulatory frameworks, and the scarcity of historical data.
Why Read? Staying up to speed on autonomous vehicles is critical for insurers.
Explore More in the March/April 2025 Actuarial Review
Check out the top 15 most popular 2024 CAS research papers in the upcoming issue of Actuarial Review.
CAS Research Resources
Find CAS research by topic in the CAS Research Library, Variance and CAS E-Forum at https://eforum.casact.org/ and Variance sites.
