{"paper_id":"2311.07597","title":"Enhancing Actuarial Non-Life Pricing Models via Transformers","authors":["Alexej Brauer"],"paper_date":"2023-11-10","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2311.07597v2","page_url":"https://thequant.space/flowcharts/enhancing-actuarial-non-life-pricing-models-via-transformers/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes novel transformer‑based methods (CAFTT, LocalGLMftt) to enhance actuarial non‑life pricing models for tabular data.","quote":"Our paper contributes to this current journey via novel methods to enhance actuarial non-life models with transformer models for tabular data.","summary":"Currently, there is a lot of research in the field of neural networks for non-life insurance pricing. The usual goal is to improve the predictive power via neural networks while building upon the generalized linear model, which is the current industry standard. Our paper contributes to this current…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The response variable Y follows an exponential dispersion family (EDF).","type":"statistical","stated":"explicit","quote":"The main assumption for a glm is that Y follows an exponential dispersion family (EDF)."},{"assumption":"All covariates xi are numerical after dummy or one‑hot encoding.","type":"data","stated":"explicit","quote":"We assume here that all covariables xi are numerical (i.e. ∈Rk), so for example, a dummy or one hot encoding is applied beforehand."},{"assumption":"Poisson regression with exposure vi is appropriate for claim frequency.","type":"model","stated":"explicit","quote":"In the case of a Poisson regression with exposure vi, for i ∈{1, . . . , n} the i’th prediction would be given by: ˆyi = exp(β0 + ⟨β, xi⟩)vi"},{"assumption":"Default hyper‑parameter settings are used for transformer models (no tuning).","type":"execution","stated":"explicit","quote":"the performance is still moderate. This can be traced back to the fact that we didn’t perform any hyperparameter tuning and used the default hyperparameter settings."}]},"datasets":{"status":"available","items":[{"name":"French motor third‑party liability claims frequency dataset (FreMTPL2freq)","provider":"Dutang and Charpentier (2018)","kind":"benchmark","access":"public","period":null,"universe":null,"quote":"The dataset of choice is the well-known French motor third‑party liability (MTPL) claims frequency dataset FreMTPL2freq Dutang and Charpentier (2018)."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"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":"Transformer‑based models (FTTdef, CAFTTdef, LocalGLMfttdef) clearly outperform their FNN‑based counterparts.","kind":"performance","quote":"At this stage, we already see that the transformer‑based models (FTTdef, CAFTTdef, LocalGLMfttdef) clearly outperform their FNN‑based counterparts (FNNEMB,CANN, LocalGLMnet)."},{"finding":"CAFTT sets a new benchmark on the FreMTPL2freq dataset.","kind":"performance","quote":"Especially the results for the CAFTT are setting, to the best of our knowledge, a new benchmark on this very popular dataset."},{"finding":"Average predicted claims frequency of transformer models is substantially far from the true mean of 7.35%.","kind":"predictive-accuracy","quote":"the average predicted claims frequency avg(ˆy) on the test dataset is in comparison to the Poisson GLMs substantially far away from the true mean of 7.35%."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":17,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"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":1,"extracted_at":"2026-11-14T18:19:45Z"},"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/"}