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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

10 results for “ratemaking”

Geographic ratemaking with spatial embeddingsstat.AP

Paper presents a method for geographic ratemaking using spatial embeddings.

problem Lack of historical loss data in areas with high exposures.

method Construct spatial features within a complex representation model and use them as inputs to a predictive model.

result Predictions have smaller bias and variance than other spatial interpolation models.

ratemaking spatial embeddings insurance geographic risk management

2021-04-26abs ↗pdf ↗

Risk Loadings in Classification Ratemakingstat.AP

A new method calculates risk loadings in classification ratemaking without subjective parameters.

problem Subjective risk loading parameters in classification ratemaking.

method Bootstrap method to calculate total risk premium, then determine risk loading parameters using quantile regression models.

result Risk premiums calculated by the new method reasonably differentiate different risk classes.

classification ratemaking risk loadings bootstrap method quantile regression heterogeneity

2020-02-05abs ↗pdf ↗

Synthetic data for ratemaking: imputation-based methods vs adversarial networks and autoencodersstat.ML

Paper compares MICE-based methods to deep generative models for synthetic data in ratemaking.

problem Limited access to high-quality data for actuarial ratemaking.

method Benchmarked MICE-based models against VAEs and CTA-GANs.

result MICE-based models preserve marginal distributions and multivariate relationships better than deep models.

synthetic data ratemaking MICE VAE GAN

2025-09-02abs ↗pdf ↗

Leveraging LLMs for Unstructured Claims Data Analysisq-fin.MF

LLMs help automate extraction of actuarial variables from unstructured claims data.

problem Manual processing of unstructured claims data is time-consuming and inconsistent.

method Two-stage processing architecture using LLMs, modular Python pipeline.

result LLM-based extraction achieved high accuracy and practical actuarial value.

LLMs unstructured data actuarial variables insurance reserving

2026-06-04abs ↗pdf ↗

Synthesizing Property & Casualty Ratemaking Datasets using Generative Adversarial Networksstat.ML

Generative adversarial networks create synthetic insurance datasets from confidential originals.

problem Difficulty in accessing or sharing confidential insurance datasets for research.

method Design and use of three GAN architectures tailored for multi-categorical insurance data.

result MC-WGAN-GP synthesizes the best data, CTGAN is easiest to use, and MNCDP-GAN ensures differential privacy.

Generative Adversarial Networks Insurance Ratemaking Synthetic Data Privacy Differential Privacy

2020-08-13abs ↗pdf ↗

Towards Explainability of Machine Learning Models in Insurance Pricingq-fin.RM

Paper aims to make insurance models more understandable.

problem Lack of transparency in machine learning models for insurance pricing.

method Proposes a framework for explaining machine learning models in insurance ratemaking.

result Illustrates the proposed framework with a case study.

Insurance Pricing Machine Learning Model Interpretability Explainability

2020-03-24abs ↗pdf ↗

The partial damage loss cover ratemaking of the automobile insurance using generalized linear modelsq-fin.RM

It is illustrated a methodology to compute the pure premium for the automobile insurance (claim frequency and severity) using generalized linear models. It is obtained the pure premium for the partial damage loss cover (PPD) using a set of automobile insurance policies with an exposition of a year. It is found that the…

2017-07-12abs ↗pdf ↗

Cyber Risk Taxonomies: Statistical Analysis of Cybersecurity Risk Classificationscs.CR

Paper analyzes cyber risk classifications for forecasting performance.

problem Lack of effective out-of-sample forecasting performance in current cyber risk classifications.

method Rolling window analysis using threshold weighted scoring functions.

result Dynamic and impact-based cyber risk classifiers outperform others in forecasting future cyber risk losses.

cyber risk forecasting risk classification cyber insurance cyber risk management

2024-10-04abs ↗pdf ↗

mSHAP: SHAP Values for Two-Part Modelsstat.ML

mSHAP explains predictions of two-part models, improving fairness and interpretability.

problem Interpreting predictions from two-part models, especially in insurance.

method mSHAP: a method for computing SHAP values of two-part models using the SHAP values of individual models.

result mSHAP is exponentially faster than kernelSHAP for computing approximate SHAP values.

two-part models insurance SHAP values interpretability fairness

2021-06-16abs ↗pdf ↗

A Portfolio-Anchored Frequency-Severity Risk Index for Trip and Driver Assessment Using Telematics Signalsstat.AP

Paper proposes a risk index combining frequency and severity of abnormal driving patterns.

problem Assessing driver risk based on telematics data.

method Combines frequency of abnormal driving patterns with severity quantified through tail rarity.

result Developed a risk index that enables reliable discrimination and ranking of drivers.

driver risk telematics risk index frequency-severity tail rarity

2026-03-16abs ↗pdf ↗