Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

2815618421,122 · Jun 202019922001200920172026
48 results for insurance data

Enhances insurance loss models using InsurTech data and machine learning.

problem Traditional insurance loss models lack predictive accuracy due to limited data sources.
method Combining proprietary claims data with InsurTech data and applying machine learning techniques.
result Improved predictive accuracy of the loss model through machine learning.

This paper explores how machine learning can improve life insurance risk assessment.

problem Limited use of machine learning in life insurance due to statistical models' efficiency.
method Review and extension of traditional actuarial methodologies with machine learning techniques.
result Developed Python library for life insurance data, improving risk modeling.

Study tackles imbalanced data in car insurance claims prediction.

problem Predicting rare events (claims) in car insurance with imbalanced data.
method Various machine learning techniques (logistic-regression, decision tree, random forest, xgBoost, feed-forward network) applied to imbalanced dataset.
result Comparison of machine learning algorithms' performance in claim occurrence prediction.

One of the impediments in advancing actuarial research and developing open source assets for insurance analytics is the lack of realistic publicly available datasets. In this work, we develop a workflow for synthesizing insurance datasets leveraging CTGAN, a recently proposed neural network architecture for generating …

2019-12-05abs ↗pdf ↗

Paper models demand and solvency for index insurance, combining traditional and measurable index-based coverage.

problem Reducing protection gaps for emerging risks.
method Develops a model for demand and solvency conditions, combining traditional and index-based insurance.
result Deduces a product that benefits from both traditional and index-based insurance approaches.

Study finds environmental liability insurance reduces industrial carbon emissions.

problem Reduction of industrial carbon emissions.
method Two-way fixed effect model using provincial (city) level panel data from 2010 to 2020.
result Environmental liability insurance reduces industrial carbon emissions at both direct and indirect levels, with varying effects.

Study shows conventional data prep fails for insurance data, proposing new methods.

problem Challenges in data preparation for insurance data lead to unreliable models.
method Proposes a new data preparation framework using support points and Chatterjee correlation coefficient.
result New methods significantly enhance model robustness and reduce computational resource requirements.

Bayesian CART models improve insurance claims frequency prediction and interpretation.

problem Improving accuracy and interpretability in insurance pricing models.
method Introducing Bayesian CART models for claims frequency, implementing MCMC algorithm for posterior tree exploration, and using DIC for model selection.
result Bayesian CART models can better classify policy-holders into risk groups.

InfDetect detects e-commerce insurance fraud using graph analysis.

problem Detecting fraudulent claims in e-commerce insurance with multiple parties involved.
method Developed a large-scale fraud detection system InfDetect using graph-based approaches.
result InfDetect successfully detected thousands of fraudulent claims and saved money daily.

Study shows insurance industry in North Macedonia declined 10% due to COVID-19.

problem Impact of COVID-19 on insurance industry activity.
method Seasonal autoregressive models and data analysis for 11 insurance classes.
result Insurance activity in North Macedonia decreased by more than 10% during the pandemic.

Method reconstructs hidden Markov chains from insurance data.

problem Recovering hidden Markov chains from incomplete insurance data.
method Neural architecture to explicitly provide transition probabilities.
result Neural model successfully validates decompression of insurance information.

The article proposes a method to make valid insurance claim predictions without relying on specific models.

problem Prediction of insurance claims using statistical models can be unreliable due to model misspecification, selection effects, and lack of finite-sample validity.
method The article employs conformal prediction, a machine learning strategy that is model-free and tuning-parameter-free, ensuring finite-sample validity.
result The proposed method guarantees valid predictions at a pre-assigned coverage probability level and performs well in insurance applications, including meeting Solvency II requirements.

Study aims to measure and mitigate biases in motor insurance pricing.

problem Ethical biases in motor insurance pricing that affect fairness and regulatory compliance.
method Statistical methodologies and data analysis to measure and mitigate biases.
result Developed tools to measure and mitigate ethical biases in motor insurance pricing.

The paper proposes an original methodology for constructing quantitative statistical models based on multidimensional distribution functions constructed on the basis of the insurance companies' data on inshurance policies (including policies with deductible) and claims incurred. Real data of some Russian insurance comp…

2019-08-14abs ↗pdf ↗

Study models weather index insurance pricing by insurers and farmers, finding flexible pricing kernels boost profits.

problem Monopoly pricing of weather index insurance with risk and flexibility considerations.
method Bowley-type sequential game with insurer and farmer, using neural networks for farmer's payoff.
result Flexible pricing kernels increase insurer profits closer to indemnity insurance levels.

The paper discusses methods for interval estimation of coefficients in penalized regression models for insurance data.

problem Valid inference on coefficients after feature selection in GLM family for insurance data.
method Proposes methodologies for constructing confidence intervals of coefficients after feature selection in GLM family.
result Valid inference on coefficients after feature selection in GLM family for insurance data.

Study insurance pricing under correlation ambiguity without increasing prices or reducing utility.

problem Understanding the dependence structure between insurance and financial risks.
method Dynamic equilibrium analysis of insurance pricing with worst-case beliefs.
result Correlation ambiguity does not necessarily increase insurance prices or reduce insurers' utility.

New model for disability insurance reserving handles delays in claim information.

problem Disability insurance claims are affected by long delays and adjudication processes.
method Proposes a new individual reserving model for real-time claim evolution.
result Shows that new reserves can be calculated as modifications of classic reserves.

Study compares machine learning models for insurance pricing, including neural networks and GLMs.

problem Improving insurance pricing models using machine learning techniques.
method Benchmark study using four insurance datasets, comparing GLMs, GBM, FFNN, and CANN.
result CANNs provide better performance than GLMs and GBM, especially for frequency and severity modeling.

Paper proves Pareto efficient insurance for multiple entities.

problem Optimizing insurance for multiple policyholders and insurers.
method Sum-minimization characterization and pairwise implementability analysis.
result Characterization of Pareto efficient insurance arrangements.

Paper defines AI-specific loss reconstruction problem and introduces CER framework.

problem Reconstructing AI-generated losses, especially in agentic systems.
method CER framework: C (control boundary), E (evidence reconstruction), R (insurance response).
result Defines AI-specific reconstruction problem and operationalizes it.

Study clusters Kenyan medical insurance companies based on financial performance and reporting consistency.

problem Identifying financial health and reporting consistency in Kenyan medical insurance companies.
method Advanced clustering techniques (KMeans, DTW) on financial ratios and time series data.
result Four distinct clusters identified, each representing different financial performance and reporting consistency combinations.

Optimizes insurance pricing by accounting for policyholders' price sensitivity.

problem Traditional insurance pricing does not consider policyholders' price sensitivity.
method Formulates insurance pricing as a decision-making problem and uses off-policy evaluation and stochastic control.
result Neural networks outperform existing techniques for policy optimization.

Paper develops methods for fair insurance pricing without direct access to sensitive attributes.

problem Fairness in insurance pricing with restricted access to sensitive attributes.
method Develops statistical methods for estimating discrimination-free premiums using privatized sensitive attributes.
result The proposed methods enable fair insurance pricing while respecting privacy and regulatory constraints.

TabPFN doesn't outperform GLM and XGBoost for motor insurance pricing.

problem Improving insurance pricing models using Tabular Foundation Models (TFMs).
method Pre-training on synthetic datasets and in-context learning for inference.
result TabPFN does not consistently outperform established baselines, has longer inference times, and is sensitive to training set size.

EBM improves car insurance claim severity and frequency prediction while maintaining interpretability.

problem Balancing predictive accuracy and interpretability in insurance claim modeling.
method Combines GAM and cyclic gradient boosting, providing interpretable predictions.
result EBM outperforms benchmark models in claim severity and frequency prediction.

Study on systemic risk in European insurance sector, showing insurer connections during stress.

problem Understanding systemic risk connectedness in European insurance sector.
method Common connectedness framework applied to returns, volatility, value-at-risk, and expected shortfall.
result Insurers are a significant component of systemic risk connectedness, especially during stress episodes.

The paper examines how risk reduction and insurance choices interact under convex premium principles.

problem Interaction between self-protection and insurance demand under convex premium principles.
method Investigates optimal prevention efforts and insurance shares using distortion risk measures.
result Self-protection and insurance are complementary, but ex ante moral hazard can turn this into a substitution effect.

Framework monitors insurance pricing models for drift and recalibration.

problem Maintaining predictive performance of pricing models in evolving insurance portfolios.
method Formalizes deviance loss and Murphy's score, studies Gini score, develops monitoring framework.
result Framework guides decisions on refitting or recalibrating pricing models.