You can find all videos at the bottom of this page.
ASTIN Session live on actuview | 12 May, 13.00–14.30 CEST
ASTIN Live Session on Data Anomalies & Costumer Behaviour (Recording available)
ASTIN Recorded Sessions | 12 May, from 9.00 CEST
Discrimination-free Insurance Pricing
Mario Wüthrich (RiskLab, ETH Zurich)
The Effect of Disruption in Insurance Industry: Instant Policy Pricing and Cyber Risk Evaluation
Valeria D‘Amato (University of Salerno), Paola Fersini (Luiss Guido Carli University), Salvatore Forte (Università Telematica Giustino Fortunato), Guiseppe Melisi (University of Sannio)
From Generalized Linear Models to Neural Networks, and Back
Mario Wüthrich (RiskLab, ETH Zurich)
Asymptotic Tail Probability of the Discounted Aggregate Claims under Homogeneous, Non Homogeneous and Mixed Poison Risk Model
Franck Adekambi (University of Johannesburg)
Approximate Bayesian Computation to Handle Aggregated Insurance Data
Pierre-Olivier Goffard (Université Claude Bernard Lyon 1 – ISFA)
The Key Role of Actuaries in Steering IFRS 17 KPIs
Baptiste Brechot (Deloitte), Redouan Hmami (Deloitte)
Actuaries Climate Risk Index: Research Update
Steve Jackson (American Academy of Actuaries)
Moral Hazard in Supplementary Health Insurance: Modelling of the Insured‘s Behaviour and the Optimal Contract
Costin Oarda (CSS Insurance)
One-year Premium Risk and Emergence Pattern of Ultimate Loss Based on Conditional Distribution
Marcin Szatkowski (ERGO Hestia), Łukasz Delong (SGH Warsaw School of Economics)
Joint Model Prediction and Application to Individual-level Loss Reserving
Peng Shi (Wisconsin School of Business)
How Can We Quantify Cyber Risk Based on Heterogenous and Volatile Data?
Sébastien Farkas (Sorbonne Université – LPSM), Olivier Lopez (UPMC), Maud Thomas (UPMC)
Believing the Bot – Model Risk in the Era of Deep Learning
Ronald Richman (QED)
Cash Flow and Unpaid Claim Runoff Estimates Using Mack and Merz-Wüthrich Models
Mark Shapland (MILLIMAN)
Regression Models for the Joint Development of Individual Payments and Claims Incurred
Łukasz Delong (SGH Warsaw School of Economics), Mario Wüthrich (RiskLab, ETH Zurich)
Multivariate Hawkes Process for Cyber Risk Insurance
Caroline Hillairet (ENSAE)
Agent Based Models: Dynamics, Stochastics and Rule Based Decisions – A Model Study.
Magda Schiegl (University of Applied Sciences Landshut)
Will P2P Insurance Replace Traditional Insurance?
Charles Davenne (University Paris Ouest Nanterre, EconomiX / Yakman)
Resource Exploitation in a Stochastic Horizon Under Two Parametrics Interpretations
Jose Daniel Lopez Barrientos (Universidad Anahuac Mexico)
Application of Machine Learning Methods for Cost Prediction of Natural Hazard in France
Antoine Heranval (Sorbonne Université / Mission Risques Naturels), Olivier Lopez (Sorbonne Université), Maud Thomas (ISUP/Sorbonne Université)
How to Improve the Performance of a Neural Network with Unbalanced Data for Text Classification in Insurance Application
Isaac Cohen Sabban (Sorbonne/Pacifica), Olivier Lopez (Sorbonne Université), Yann Mercuzot (Pacifica)
CORT: the Copula Recursive Tree
Oskar Laverny (Scor, Université Claude Bernard Lyon 1), Véronique Maume-Deschamps (Université Claude Bernard Lyon 1), Didier Rullière (Université Claude Bernard Lyon 1), Esterina Masiello (Université Claude Bernard Lyon 1)
Accumulation Scenarios for Cyber Insurance Based on Epidemiological Models.
Olivier Lopez (UPMC), Caroline Hillairet (Ensae Paris, Crest)
AGLM: A Hybrid Modeling Method of GLM and Data Science Techniques
Suguru Fujita (FIAJ, CERA), Toyoto Tanaka (FIAJ), Kenji Kondo (FIAJ), Hirokazu Iwasawa (FIAJ)
Generalized Pareto Regression Trees for Extreme Claims Prediction
Maud Thomas (UPMC), Olivier Lopez (UPMC)
Premium Rating Without Losses – How to Estimate the Loss Frequency of Loss-free Risks
Michael Fackler (Consulting Actuary)
Non-Affirmative Cyber Assessment Framework
Visesh Gosrani (CyDelta)
Best Estimate(s): Who Will Get the Best One? Cognitive Biases and Expert Judgement Applied to P&C Reserving
Simon Robert (Deloitte)
Can Machine Learning Algorithms Outperform Traditionally Used Methods in Insurance Pricing?
Harej Bor (PRS)
Measuring the Value of Risk Cost Models
Dimitri Semenovich (Insurance Australia Group)
Scenario Testing for Flatrated Fleets During the Yearly Price Adjustment Process – a Practical Example
Michael Klamser (Allianz)
Social Inclusion in the World of Modern Predictive Analytics
(joint session with IACA)
Esko Kivisaari (Finance Finland)
The comparison of different algorithms for insurance pricing exercise is a task that relies heavily on the data sample used. There are two options: real data and synthetic data. A critical issue with the real data is the lack of information of the exact u
Following innovations in machine learning and computational statistics, a large variety of new modeling techniques are being applied to premium rating. In order to carry out model comparison and selection in this regime it is particularly valuable to deve
This presentation focuses on the problem of moral hazard in health insurance. We introduce our solution by explaining how we have modelled the behaviour of supplementary health insurance policyholders within a context of moral hazard and build an Optimal
In this paper, we develop stochastic models to determine the impact of a massive cyber attack on an insurance portfolio. The model is based on the classical SIR framework (Susceptible - Infected - Recovered) of epidemiological models. For a given type of
In insurance and even more in reinsurance it occurs that about a risk you only know that it has suffered no losses in the past say seven years. Some of these risks are furthermore such particular or novel that there are no similar risks to infer the loss
The American Academy of Actuaries (Academy) would be pleased to present Actuaries Climate Risk Index (ACRI): Research Update. The ACRI is derived from a model of the statistical relationship between the weather components of the Actuaries Climate Index (A
Approximate Bayesian Computation (ABC) is a statistical learning technique to select and calibrate models in an automated fashion using the data at hand. It consists in simulating synthetic data from the potential models and assessing the distance between
In this talk, we present a two-player extraction game where the random terminal times follow (different) heavy-tailed distributions which are not necessari!y compactly supported. Besides, we de!ve on the implications of working with logarithmic utility/te
In this paper we propose an actuarial framework and a statistical methodology allowing the quantification of Cyber claims resulting from data breaches events even when applied on few and heterogeneous data. Indeed, for now, just a few Cyber insurance clai
We study the relation between one-year premium risk and ultimate premium risk. In practice, the one-year risk is sometimes related to the ultimate risk by using a so-called emergence pattern formula introduced by England et al. (2012) and Bird, Cairns (20
The (re)lnsurance industry is faced with a growing risk related to the development of information technology (IT). This growth is creating an increasingly digitally interconnected world with more and more dependance being placed on IT systems to manage pr
Tree-based methods are convenient and powerful machine learning tools thatcan be seen as alternatives to classical regression and prediction models suchas generalized linear models, see for example. The most standard proceduresare designed to estimate the
Outstanding claims reserving have become most of the time Best Estimate whereas they used to be appropriate. These reserves should now be equal to the best estimate of the cost of the claims not yet settled and not yet reported. Even if new reserving meth
The international IFRS 17 standard will have a major impact on the valuation and accounting of insurance contracts and therefore on the profit signature of insurance companies.Actuaries have a central role in new standard implementation. They are strongly
A simple formula for non-discriminatory insurance pricing is introduced. This formula is based on the assumption that certain individual (discriminatory) policyholder information is not allowed to be used for insurance pricing. The suggested procedure can
The insurance industry are embracing innovation and technology where are not only Millennials and Generation Y customers accounted for the majority of online insurance sales. The InsurTech is breaking the paradigms affecting the insurance market by introd
One of the first in the actuariat literature published agent based models (ABM) is by Ingram et al. The paper describes a model of a competitive (insurance) market that shows cyclical behavior. The authors put their focus on the model’s theoretic fo
Leveraging from the patchwork copula formalization and from various piecewise constant density estimators (minimum-distance based, tree-shaped, Bayesian partitioning, Delaunay tree, Voronoi histogram), we derive a flexible, consistent, piecewise constant
We discuss the statistical modeling cycle. This discussion highlights on how to enhance classical generalized linear models by neural network features. On the way to get there, we mention traps and pitfalls that need to be avoided to get good statistical
In this work, we propose a methodology to predict the total cost of a natural catastrophe shortly after itsoccurrence. Thanks to a large database provided through a partnership with Federation Francaise d'Assurance,we manage to have access to a very la
For both Solvency II and IFRS 17 the actuary can use unpaid claim variability estimates for cash flows and the runoff of unpaid claims in addition to the more widely used accident year view of the unpaid claims. This paper is based on a review of the foun
In recent years, one of the most critical tasks for actuaries is to adopt data science techniques in predictive modeling practice. However, due to the peculiarity of insurance data as well as the priorities taken by actuaries in decision-making, such as t
Among the several features of cyber-attacks one wants to reproduce, those related to the memory of events and self-exciting behavior is of major importance, as it underlies the clustering and auto-correlation of times of cyber-attacks. In this paper, we p
In 2019, Alibaba reinvents healthcare thanks to a P2P insurance model which has been a huge commercial success with more than 100 million users in China.Despite commercial failures of most P2P models (B2C) attempts in Europe, Alibaba proves that P2P model
In non-life insurance, the payment history can be predictive of the timing of a settlement for individual claims. Ignoring the association between the payment process and the settlement process could bias the prediction of outstanding payments. To address
The goal of this paper is to jointly model the development of individual daim payments and daims incurred. Our analysis only focuses on the development of the so-called Reported But Not Settled (RBNS) daims. We develop regression models and postulate dist
The volume of digital data is increasing by around 61 % annually. The rapidly developing techniques of predictive analytics make it possible to use this data in underwriting and pricing of insurers. These novel technologies present huge opportunities for
Deep Learning models are currently being introduced into business processes to support decision-making in insurance companies. At the same time model risk is recognized as an increasingly relevant field within the management of operational rlsk that tries