{"paper_id":"2611.21326","title":"Neural Marked Point Processes for Health Insurance Claims","authors":["Eva Flonner"],"paper_date":"2026-11-16","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2611.21326","page_url":"https://thequant.space/flowcharts/neural-marked-point-processes-for-health-insurance-claims/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a neural marked point‑process model that combines history‑dependent, type‑specific claim intensities with conditional severity distributions, reporting delays and stochastic medical‑cost inflation.","quote":"In this paper, we propose a neural marked point-process model for individual health insur-ance claims that combines history-dependent, type-specific claim intensities with conditional distributions of claim amounts.","summary":"Health insurance claims exhibit temporal dependence, as previous claims may provide information about the timing, type and amount of subsequent claims. Such dependencies are difficult to capture with traditional actuarial models based on aggregated claim counts. We investigate a neural marked point…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Claim intensities are modeled as conditional intensities derived from a causal Transformer representation of past claims.","type":"model","stated":"explicit","quote":"We investigate a neural marked point process in which a causal Transformer represents individual claim histories and determines type-specific conditional intensities, allowing for self-excitation and interactions between claim types.","support":"full"},{"assumption":"Medical‑cost inflation follows a stochastic process with a common long‑run drift centered at 3% per year.","type":"statistical","stated":"explicit","quote":"Weakly informative priors constrain the drift and innovation scales; in particular the common long-run drift is centered at 3% per year in the fitted configuration.","support":"full"},{"assumption":"Reporting delays and exposure periods are correctly captured by the observation structure described (policy exposure, pre‑sample period, etc.).","type":"data","stated":"explicit","quote":"Particular attention is given to the observation structure of insurance data, including differences in policy exposure, reporting delays and changes in medical costs over calendar time.","support":"full"},{"assumption":"The logarithmic transformation of claim amounts and a mixture of three Gaussian components adequately model the conditional severity distribution.","type":"model","stated":"explicit","quote":"The logarithmic transformation allows the model to describe positive claim amounts on an unrestricted numerical scale, while Mk(t) accounts for the cumulative effect of medical inflation on claim amounts of type k up to time t. The remaining variation is modeled using a mixture of three Gaussian distributions.","support":"full"},{"assumption":"The simulated portfolio (10,000 contracts) is representative for evaluating recovery of known claim dynamics.","type":"execution","stated":"explicit","quote":"A simulation study with 10,000 insurance contracts examines the recovery of known claim dynamics, while an application to MEPS-derived medical-event data assesses predictive performance.","support":"full"},{"assumption":"The MEPS‑derived medical‑event data are sufficiently detailed to assess predictive performance of the model.","type":"data","stated":"explicit","quote":"The processed sample contains 5,447 individuals, with 21,001.5 person-years and 436,542 recorded events.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Simulated insurance portfolio","provider":null,"kind":"synthetic","access":"public","period":null,"universe":null,"quote":"A simulation study with 10,000 insurance contracts examines the recovery of known claim dynamics, while an application to MEPS-derived medical-event data assesses predictive performance.","support":"full"},{"name":"MEPS‑based medical‑event data (Panel 24)","provider":"Medical Expenditure Panel Survey","kind":"other","access":"public","period":null,"universe":"5,447 individuals","quote":"The processed sample contains 5,447 individuals, with 21,001.5 person-years and 436,542 recorded events.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"On the MEPS data, the neural model achieves better predictive performance than two generalized linear model benchmarks in terms of claim‑count deviance and expenditure discrimination.","kind":"predictive-accuracy","quote":"On the MEPS data, the neural model achieves better predictive performance than two generalized linear model benchmarks in terms of claim-count deviance and expenditure discrimination.","support":"full"},{"finding":"The fitted model reproduces the main patterns in claim frequencies and severities, though some discrepancies remain in the tails of the distributions.","kind":"statistical","quote":"The fitted model reproduces the main patterns in claim frequencies and severities, although some discrepancies remain in the tails of the distributions.","support":"full"},{"finding":"Simulation results indicate that the proposed model captures several important features of the underlying data‑generating process, including claim frequencies, amounts, reporting delays and dependence between successive claims.","kind":"performance","quote":"Overall, the simulation results indicate that the proposed model captures several important 19 Neural marked point processes for health claims Working manuscript Figure 7: Medical cost indices relative to their initial level. The model reproduces the main patterns in claim frequencies and severities, while the agreement is less precise for some claim types and for the development of medical costs over time.","support":"full"},{"finding":"The model captures the broad development of medical costs more reliably than precise type‑specific trajectories, with reasonable posterior uncertainty bands.","kind":"statistical","quote":"Given the relatively short observation period and the potential overlap between calendar-time effects, attained age and policy duration, the results suggest that the model captures the broad development of medical costs more reliably than their precise type-specific trajectories.","support":"full"},{"finding":"Results from the simulation describe performance for a single realized portfolio and seed, not variation across independent portfolios.","kind":"other","quote":"Since the experiment uses one simulated portfolio and one random seed, the reported results describe performance for this particular realization rather than variation across independently generated portfolios.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":26,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":3,"extracted_at":"2026-11-17T15:29:17Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}