New Perspectives and Methods in Loss Reserving Using Generalized Linear Models
Bibliographic record
Abstract
Loss reserving has been one of the most challenging tasks that actuaries face since the appearance of insurance contracts. The most popular statistical methods in the loss reserving literature are the Chain Ladder Method and the Bornhuetter Ferguson Method. \n \nRecently, Generalized Linear Models (GLMs) have been used increasingly in insurance model fitting. Some \naggregate loss reserving models have been developed within the framework of GLMs (especially Tweedie distributions). In this thesis we look at loss reserving from the perspective of individual risk classes. A structural loss reserving model is built which combines the exposure, the loss emergence pattern and the loss development pattern together, again within the framework of GLMs. Incurred but not reported (IBNR) losses and Reported but not settled (RBNS) losses are forecasted separately. Finally, we use out of sample tests to show that our method is superior to the traditional methods. \n \nIn the third chapter we also extend the theory of limited fluctuation credibility for GLMs to one for GLMMs. Some criteria and algorithms are given. This is a byproduct of our work but is interesting in its own sake. The asymptotic variance of the estimators is derived, both for the marginal mean and the cluster specific mean.
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 | 0.035 | 0.062 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.005 | 0.004 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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".