4.7 Article

Modelling economic losses from earthquakes using regression forests: Application to parametric insurance

Related references

Note: Only part of the references are listed.
Article Economics

Role of insurance in wildfire risk mitigation

Devika Hazra et al.

Summary: This study examines the impact of wildfire-risk on homeownership in fire-prone zones and highlights the insufficient insurance coverage in moderate-to-high risk areas. The research findings suggest that current insurance policies do not effectively discourage homeownership in high-risk zones.

ECONOMIC MODELLING (2022)

Article Economics

The economic impacts of direct natural disaster exposure

Meliyanni Johar et al.

Summary: This study estimates the economic impacts of natural disasters on household damages or destruction. The findings show that natural disasters have no impact on employment and income, but have substantial effects on financial hardship and risk aversion. Smaller isolated disasters, which receive little government support, have particularly large impacts, while residing in a disaster zone without experiencing residential destruction has minimal effects. Age, parenthood, illness, and social support are identified as predictors of financial vulnerability to destruction. These results can inform the allocation of government assistance after future disasters.

JOURNAL OF ECONOMIC BEHAVIOR & ORGANIZATION (2022)

Article Economics

Earthquake parametric insurance with Bayesian spatial quantile regression

Jeffrey Pai et al.

Summary: Parametric insurance is widely used to insure nature-related risks. This paper proposes a Bayesian spatial quantile regression model to reduce the basis risk of earthquake parametric insurance. The model analyzes the impact of earthquake hazard, risk exposure, and vulnerability on economic loss, taking into account spatial correlation.

INSURANCE MATHEMATICS & ECONOMICS (2022)

Article Economics

ADDRESSING IMBALANCED INSURANCE DATA THROUGH ZERO-INFLATED POISSON REGRESSION WITH BOOSTING

Simon C. K. Lee

Summary: The study introduces a machine learning approach to zero-inflated Poisson (ZIP) regression, which enhances predictive accuracy through adaptive weight adjustment. The cyclic coordinate descent optimization is used to address imbalanced financial data, demonstrating significant improvement in performance through real-life data testing. The results justify the modeling techniques as compared to other popular alternatives.

ASTIN BULLETIN (2021)

Article Economics

Cyber claim analysis using Generalized Pareto regression trees with applications to insurance

Sebastien Farkas et al.

Summary: This paper proposes a method for cyber claim analysis based on regression trees to identify criteria for claim classification and evaluation. The focus is on severe/extreme claims, combining Generalized Pareto modeling and a regression tree approach. The method allows computations of central scenarios and extreme loss quantiles for a cyber portfolio.

INSURANCE MATHEMATICS & ECONOMICS (2021)

Article Economics

A random forest based approach for predicting spreads in the primary catastrophe bond market

Despoina Makariou et al.

Summary: The use of random forest for predicting catastrophe bond spreads showed better performance compared to benchmark linear regression, extracting information more effectively and capturing interactions better without specifying them. The results were stable in terms of prediction accuracy and minimal depth importance ranking. There was only a small divergence between the drivers of catastrophe bond spread in the predictive versus explanatory framework.

INSURANCE MATHEMATICS & ECONOMICS (2021)

Article Business, Finance

Boosting Insights in Insurance Tariff Plans with Tree-Based Machine Learning Methods

Roel Henckaerts et al.

Summary: This study focuses on using machine learning methods to develop comprehensive tariff plans and adjust for the specific characteristics of insurance data to establish transparent and interpretable pricing models. By utilizing decision trees in machine learning and selecting optimal tuning parameters, as well as providing visualization tools to evaluate the economic value of the new modeling approaches.

NORTH AMERICAN ACTUARIAL JOURNAL (2021)

Article Economics

The impact of earthquakes on economic activity: evidence from Italy

Francesco Porcelli et al.

EMPIRICAL ECONOMICS (2019)

Article Economics

Bayesian approaches for analyzing earthquake catastrophic risk

Yunxian Li et al.

INSURANCE MATHEMATICS & ECONOMICS (2016)

Article Statistics & Probability

Tree-based censored regression with applications in insurance

Olivier Lopez et al.

ELECTRONIC JOURNAL OF STATISTICS (2016)

Article Economics

CATASTROPHIC NATURAL DISASTERS AND ECONOMIC GROWTH

Eduardo Cavallo et al.

REVIEW OF ECONOMICS AND STATISTICS (2013)

Article Business, Finance

Tree-based methods: a useful tool for life insurance

Walter Olbricht

EUROPEAN ACTUARIAL JOURNAL (2012)

Article Statistics & Probability

Summarizing Insurance Scores Using a Gini Index

Edward W. Frees et al.

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION (2011)

Article Economics

ESTIMATING THE DIRECT ECONOMIC DAMAGES OF THE EARTHQUAKE IN HAITI

Eduardo Cavallo et al.

ECONOMIC JOURNAL (2010)

Article Economics

Economic development and the impacts of natural disasters

Hideki Toya et al.

ECONOMICS LETTERS (2007)

Article Economics

Earthquake fatalities: the interaction of nature and political economy

N Anbarci et al.

JOURNAL OF PUBLIC ECONOMICS (2005)

Article Statistics & Probability

Maximum likelihood regression trees

XG Su et al.

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS (2004)

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)