{"paper_id":"2508.02283","title":"An Enhanced Focal Loss Function to Mitigate Class Imbalance in Auto Insurance Fraud Detection with Explainable AI","authors":["Francis Boabang","Samuel Asante Gyamerah"],"paper_date":"2025-08-04","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.02283v1","page_url":"https://thequant.space/flowcharts/an-enhanced-focal-loss-function-to-mitigate-class-imbalance/","scores":{"empirical_rigor":7.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a structured three-stage training framework that uses a convex surrogate loss, an intermediate non‑convex loss, and the standard focal loss to improve fraud detection under severe class imbalance.","quote":"This paper proposes a structured three-stage training framework that integrates a convex surrogate of focal loss for stable initialization, a controlled non-convex intermediate loss to improve feature discrimination, and the standard focal loss to refine minority-class sensitivity.","summary":"In insurance fraud prediction, handling class imbalance remains a critical challenge. This paper presents a novel multistage focal loss function designed to enhance the performance of machine learning models in such imbalanced settings by helping to escape local minima and converge to a good…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The convex surrogate loss remains convex when the weight wt is fixed and the focusing parameter γ is chosen so that 1 − γpt > 0.","type":"model","stated":"explicit","quote":"The convexity result therefore holds under the assumption that wt is fixed and that we analyse the loss as a function of pt"},{"assumption":"The dataset is highly imbalanced with far fewer fraudulent cases than legitimate ones.","type":"data","stated":"explicit","quote":"The dataset is usually highly skewed, with legitimate (non‑fraudulent) cases becoming more than the fraudulent ones. Formally, |{yi = 1}| ≪ |{yi = 0}|, resulting in bias…"},{"assumption":"Deep sequential (LSTM) models are used and their overall problem is not convex, but a convex surrogate in logit space provides a well‑conditioned initial phase.","type":"model","stated":"implied","quote":"Thus, while the convex warm start confines the optimisation trajectory to a locally well‑conditioned region in logit space, the LSTM mapping remains intrinsically non‑convex."}]},"datasets":{"status":"available","items":[{"name":"Proprietary auto‑insurance claims dataset","provider":"large U.S. insurer","kind":"other","access":"proprietary","period":null,"universe":null,"quote":"The empirical analysis uses a dataset of automobile insurance claims from a large U.S. insurer. The sample contains 39,981 records, each associated with a single customer, and 39 explanatory variables describing policy, vehicle, customer, and claim characteristics."}],"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":"The three‑stage schedule delivers the most balanced and reliable performance across accuracy, precision, recall, F1 score, and AUC, outperforming both convex‑only and non‑convex‑only baselines.","kind":"performance","quote":"Using accuracy, precision, recall, F1 score, and AUC as evaluation metrics, we found that the three‑stage schedule delivers the most balanced and reliable performance"},{"finding":"The staged transition from convex to non‑convex learning produces a sparse, well‑regularized SHAP attribution profile with moderate, bounded feature importance magnitudes.","kind":"predictive-accuracy","quote":"The staged transition from convex to non‑convex learning led to selective and well‑regularized feature utilization, producing a sparse and structured attribution profile"}],"reported_performance":null,"out_of_sample":{"method":"cross-validation","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":11,"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":true,"code_url":"https://github.com/boabangf/Efficient-Focal-Loss-Function-for-Insurance-Fraud-Prediction","note":null},"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":"2026-11-14T17:30:31Z"},"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/"}