Investigating the effect of climate-related hazards on claim frequency prediction in motor insurance with incomplete data
Bibliographic record
Abstract
Abstract A climate-related dataset provided by a Greek insurance company is analysed to quantify the risks that weather-related hazards, driven by climate change, pose to motor insurance. However, accurately modelling the relationship between these hazards and claim frequencies is challenging, largely because the available records are incomplete. Specifically, they capture only those storm events that result in at least one claim while omitting unreported events. To address this limitation, we introduce a novel class of compound frequency models for the joint analysis of storm occurrences and the corresponding claim frequencies with accurate predictive power. These models are specifically designed to recover the joint distribution of actual storm events and underlying claim processes even when faced with incomplete data. Additionally, we incorporate geospatial covariates to evaluate their influence on both storm occurrences and claim frequencies. Given Greece’s vulnerability to extreme weather due to its geographical position, understanding the influence of climate change on insurance risks is critical. Notably, our findings reveal a negative intrinsic dependence between actual storm counts and per-storm claim frequencies, suggesting potential diversification benefits for insurers as climate change leads to more frequent weather-related hazards.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.038 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".