CANN models improve insurance claim count predictions using telematics data.
problem Improving insurance claim count predictions with telematics data.
method Combining classical actuarial models with neural networks for telematics data.
result CANN models outperform traditional models in predicting insurance claims.
Develops a method to model multivariate count processes with Cox processes and shot noise intensities.
problem Modeling and estimating dependent count processes using granular data.
method Multivariate Cox process with shot noise intensities, connected via Lévy copulas.
result Allows for over-dispersion, auto-correlation, and realistic features in count processes.
New model bridges pricing and reserving for insurance claims.
problem Incomplete claim data due to reporting and settlement delays.
method Develops an occurrence and development model to estimate both claims and premiums.
result Effective resolution of pricing and reserving inconsistencies.
We study hedging and pricing of unattainable contingent claims in a non-Markovian regime-switching financial model. Our financial market consists of a bank account and a risky asset whose dynamics are driven by a Brownian motion and a multivariate counting process with stochastic intensities. The interest rate, drift, …
Enhances count process modelling with Markov-modulated non-homogeneous Poisson process.
problem Count data modelling challenges, especially in complex scenarios.
method Introduces a flexible frequency perturbation measure into Markov-modulated Poisson process framework.
result Natural incorporation of observed event arrivals and latent factors.
Classification is the task of predicting the class labels of objects based on the observation of their features. In contrast, quantification has been defined as the task of determining the prevalences of the different sorts of class labels in a target dataset. The simplest approach to quantification is Classify & Count…
Study assesses health plan risk measures for Solvency Capital Requirement.
problem Assessing risk measures for health plans to meet Solvency Capital Requirement.
method Three-part regression model with three GLMs for claim counts, episode allocation, and severity.
result Reduction in regression models compared to traditional methods.
In this paper we provide a valuation formula for different classes of actuarial and financial contracts which depend on a general loss process, by using the Malliavin calculus. In analogy with the celebrated Black-Scholes formula, we aim at expressing the expected cash flow in terms of a building block. The former is r…
Language models allocate information storage, not collapsing into uniform representations.
problem Incomplete neural collapse in language model representations.
method Analyzing variance and information sharing across 14 models, proving an information floor.
result Within-class variance is allocated information storage, not collapsed into uniform representations.
Reinforcement learning improves insurance claims reserving by learning from all claim trajectories.
problem Traditional reserving models learn only from settled claims, missing valuable data from ongoing claims.
method Formulated as a Markov decision process, uses reinforcement learning to update OCL estimates sequentially.
result Soft Actor-Critic implementation achieves competitive claim-level accuracy and strong aggregate performance.
The study analyzes how bonus-malus systems and delayed claims settlement affect insurance companies' financial stability.
problem Analyzing the impact of bonus-malus systems and delayed claims settlement on insurance companies' financial stability.
method Examined a discrete-time risk model with time-varying premiums, evaluating two types of claims and settlement delays.
result Delayed settlement of by-claims leads to lower ruin probabilities under specific assumptions.
Deep Claim predicts payer responses from claims data using deep learning.
problem Predicting payer responses from claims data to improve healthcare performance.
method Learning complex dependencies in claim inputs to create a compact representation, then using deep learning to predict responses.
result Deep Claim improves claim denial prediction by 22.21%.
Counting tripods on a flat torus using lattice point counting.
problem Counting finite BPS webs in flat torus geometry.
method Lattice point counting techniques in C2. result Asymptotic counting result for tripods on the torus.
New method for individual claims reserving using machine learning.
problem Traditional claims reserving methods are limited in individual claim prediction.
method Restructured data utilization for CL prediction, using multi-period factors.
result Neural networks applied for individual claims reserving.
The tail of the distribution of a sum of a random number of independent and identically distributed nonnegative random variables depends on the tails of the number of terms and of the terms themselves. This situation is of interest in the collective risk model, where the total claim size in a portfolio is the sum of a …
Two machine learning models detect anomalies in ER claims, saving up to 40% in improper payments.
problem Improper health insurance payments from fraud and upcoding.
method Two machine learning models: an upcoding model based on severity code distributions and a random forest model for claim sorting.
result Random forest model saved 12% to 40% in improper payments compared to a baseline approach.
Optimizes insurance processing capacity to minimize costs.
problem Processing delays and backlogs in insurance claims.
method Optimal capacity selection to minimize delay-adjusted and fixed costs.
result Minimizes claims costs by balancing processing capacity and delays.
Flow Matching for count data improves sample quality and efficiency.
problem Mapping between count distributions across batches or time points in high-dimensional count data.
method count-FM, a flow-matching framework based on a continuous-time birth-death process with local unit jumps.
result count-FM achieves better sample quality than representative baselines while using fewer parameters.
This study compares the largest claims from two insurance portfolios using stochastic orderings.
problem Comparing the largest claims from two heterogeneous insurance portfolios.
method Used various stochastic orderings and established sufficient conditions associated with model parameters.
result Established sufficient conditions for comparing the largest claims from two insurance portfolios.
Model detects insurance fraud using social network analysis.
problem Fraudulent insurance claims by exaggeration or intentional damage.
method Network construction linking claims and parties, BiRank algorithm for fraud score computation, feature extraction from network and claims, supervised model building.
result Network features improve fraud detection performance.
New findings challenge the traditional U-shaped curve of model complexity and error, revealing a second descent in error as model size increases.
problem The traditional U-shaped curve of model complexity and prediction error is incomplete, with recent work suggesting a second descent in error as model size increases.
method Careful consideration of multiple complexity axes and a nonparametric statistics perspective were used to interpret the observed double descent curves.
result The observed double descent curves in classical statistical machine learning methods fold back into traditional convex shapes, resolving tensions with statistical intuition.
We consider trading in a financial market with proportional transaction costs. In the frictionless case, claims are maximal if and only if they are priced by a consistent price process--the equivalent of an equivalent martingale measure. This result fails in the presence of transaction costs. A properly maximal claim i…
Investor maximizes utility from an unknown claim using robust optimization.
problem Maximizing utility from an unknown contingent claim.
method Robust optimization with quantile formulation and variational inequalities.
result Optimal trading strategy and utility indifference price determined.
Model predicts individual insurance claim reserves using activation patterns.
problem Accurately predicting individual claim reserves in insurance contracts.
method Multinomial logistic regression to model claim activation and development.
result The model generates accurate predictions of total and per coverage reserves.
BERT learns claim descriptions to identify patent novelty.
problem Identifying novel patent claims among existing documents.
method Training BERT on concatenated claims and descriptions, scoring BERT's output.
result BERT identifies relevant X documents for patent novelty.
Insurance companies must manage millions of claims per year. While most of these claims are non-fraudulent, fraud detection is core for insurance companies. The ultimate goal is a predictive model to single out the fraudulent claims and pay out the non-fraudulent ones immediately. Modern machine learning methods are we…
Paper introduces EEMs for pricing contingent claim returns.
problem Computing expected future prices of contingent claims.
method Dynamic change of measure approach to construct EEMs.
result EEMs provide physical and pricing expectations of contingent claim prices.
Traditional non-life reserving models largely neglect the vast amount of information collected over the lifetime of a claim. This information includes covariates describing the policy, claim cause as well as the detailed history collected during a claim's development over time. We present the hierarchical reserving mod…
New theorem counts curves on orbifolds.
problem Counting curves on surfaces.
method Applied Mirzakhani's theorem to orbifolds.
result Curve counting theorem extends to orbifolds.
A new method for modeling insurance claim frequencies using random proportions.
problem Inaccurate fitting of classical distributions to insurance claim frequency data.
method Modeling claim frequencies using random proportions of insurance contracts and applying goodness-of-fit tests.
result A new statistical approach for better modeling insurance claim frequencies.
The paper introduces BCART models for aggregate claim amount, improving frequency-severity and joint modeling.
problem Modeling aggregate claim amount with frequency-severity and joint dependencies.
method Developed three types of BCART models: frequency-severity, sequential, and joint models. Used various distributions for claim severity data.
result Weibull distribution outperforms gamma and lognormal for right-skewed, heavy-tailed claim severity data.
In this work, we focus on fine-tuning an OpenAI GPT-2 pre-trained model for generating patent claims. GPT-2 has demonstrated impressive efficacy of pre-trained language models on various tasks, particularly coherent text generation. Patent claim language itself has rarely been explored in the past and poses a unique ch…
FiNCAT tool automatically identifies financial numerals in documents.
problem Differentiating between in-claim and out-of-claim numerals in financial documents.
method Extracts context embeddings of numerals using BERT, then uses Logistic Regression to classify.
result Achieved a Macro F1 score of 0.8223 on validation set.
A new method, Count-MORL, improves offline reinforcement learning by using state-action frequency.
problem Improving offline reinforcement learning performance.
method Integrates count-based conservatism into model-based offline reinforcement learning.
result The learned policy is near-optimal and outperforms existing methods.
Proposes a method to reconcile count time series forecasts.
problem No formal framework for probabilistic reconciliation of count time series.
method Generalizes Bayes' rule for reconciling real-valued and count variables.
result Improves forecast accuracy for count variables compared to Gaussian reconciliation.
A novel model-selection method for dynamic networks using synthetic data.
problem Classifying and understanding the growth mechanisms of dynamic networks.
method Training a classifier on synthetic network data generated by nine random graph models, using dynamic features that count new links.
result Achieves near-perfect classification of synthetic networks, outperforming state-of-the-art methods.
Study geodesic paths on flat surfaces, comparing length and singularity counts.
problem Comparing geometric length and singularity counts on geodesic paths.
method Apply counting limit laws to infinite graphs and then to flat surfaces.
result Statistical comparison of geometric length and singularity counts on geodesic paths.
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.
New method simplifies individual claims reserving.
problem Insufficient flexibility and robustness in existing methods.
method Building on classical chain-ladder method, introduces new perspective.
result Advances toward a new standard for micro-level reserving.
Counts arcs in surfaces, proving convergence of geodesic currents.
problem Counting arcs of the same type in compact surfaces and related geometries.
method Derives convergence of geodesic currents to prove arc counts.
result Proves convergence of geodesic currents, leading to arc counting results.
Deviance-style normalization for sparse, jointly overdispersed count matrices
problem Jointly overdispersed count matrices
method Dirichlet-multinomial deviance residualization
result Preserves exact sparsity, evaluates in constant time, recovers multinomial residual
The paper proposes count echo state networks for forecasting graduate student enrollments.
problem Forecasting graduate student enrollments from historical data.
method Developed hierarchical count echo state networks and compared them to Poisson autoregressions and negative binomial models.
result Hierarchical negative binomial based echo state network is the superior model.
Using a suitable change of probability measure, we obtain a novel Poisson series representation for the arbitrage- free price process of vulnerable contingent claims in a regime-switching market driven by an underlying continuous- time Markov process. As a result of this representation, along with a short-time asymptot…
Counted essential surfaces in a knot's exterior, finding a unique pattern.
problem Counting essential surfaces in a knot's exterior.
method Counted essential surfaces by genus, using Euler totient function. Showed normal surfaces are connected by counting their components. Used Agol, Hass, and Thurston's tools to convert component counting into orbit counting.
result Found a unique pattern in the number of essential surfaces by genus.
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.
We derive asymptotic expansions for the prices of a variety of European and barrier-style claims in a general local-stochastic volatility setting. Our method combines Taylor series expansions of the diffusion coefficients with an expansion in the correlation parameter between the underlying asset and volatility process…
Time-aware fact-checking improves veracity predictions for time-sensitive claims.
problem Fact-checking decisions should consider temporal information of claims and evidence.
method Investigated four temporal ranking methods to optimize evidence ranking for fact-checking models.
result Time-aware evidence ranking surpasses relevance assumptions and improves veracity predictions for time-sensitive claims.
New volume functions for random hyperbolic surfaces link to spectral gaps.
problem Analyzing spectral gaps in random hyperbolic surfaces.
method Introduced new volume functions VgT(l), derived their asymptotic expansions, and linked them to spectral gaps. result Coefficients in the asymptotic expansion of VgT(l) are Friedman-Ramanujan functions.