A novel Bayesian Pay-As-You-Drive insurance model with risk prediction and causal mapping
Bibliographic record
Abstract
The modern vehicle insurance industry is increasingly adopting Pay-As-You-Drive (PAYD) insurance models, aligning premium costs with driving behavior. Our study introduces a Bayesian approach to PAYD insurance, leveraging the strengths of Naive Bayes classifiers and Bayesian Networks to handle uncertainty and integrate prior knowledge in risk assessment. The Naive Bayes model achieved an 87.5% accuracy in predicting risk partitions. With the Bayesian Network providing insights into causal relationships through a Directed Acyclic Graph (DAG), we also address the challenges of traditional actuarial models — low interpretability of intra-factor relationships and thus hard to plan for risk management for both provider and policyholder. Our research contributes to optimizing insurance pricing strategies. Still, the causal mapping also dismisses the meaningfulness of using geographic grouping in insurance pricing (discriminatory or not). It reassures the theoretical advantage of the PAYD model over the traditional model, facilitating access to affordable coverage for policyholders. • Use Bayesian models to Pay-As-You-Drive insurance for more accurate risk assessment. • Train Naive Bayes that achieves 87.5% accuracy in predicting risk. • Apply domain expertise to provide “prior” in Bayesian Network causal modeling. • Utilize DAGs to model causal links between risk factors and insurance claims. • Build dynamic causal maps of driving behaviors to guide interventions.
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 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".