Oracle3
Open-source trading engine and MCP server for prediction markets. Fee-aware no-arbitrage trading across related contracts, live on Kalshi, Polymarket and Solana or on paper.
10 flagship Python libraries for UK personal lines insurance pricing. Proxy discrimination auditing (FCA Consumer Duty), model validation and governance, DML causal inference, conformal prediction, Wh
FinanceHTML · PythonGitHub @burning-costOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Burning Cost blog and course landing page — open-source insurance pricing tools for UK actuarial and data science teams
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Insurance pricing education and open-source tooling for UK actuaries and pricing teams.
The site at burning-cost.github.io publishes worked examples, methodology explainers, and links to all open-source libraries.
Ten libraries we consider genuinely differentiated — tools for hard problems in UK pricing where no adequate open-source Python solution existed before.Read the full README ↗Insurance pricing education and open-source tooling for UK actuaries and pricing teams.
The site at burning-cost.github.io publishes worked examples, methodology explainers, and links to all open-source libraries.
Ten libraries we consider genuinely differentiated — tools for hard problems in UK pricing where no adequate open-source Python solution existed before.
Regulatory compliance
| Library | Problem it solves |
|---|---|
| insurance-fairness | Proxy discrimination auditing aligned to FCA Consumer Duty and Equality Act 2010 |
| insurance-governance | PRA SS1/23 model validation reports: bootstrap Gini CI, A/E CI, double-lift, renewal cohort test |
Causal inference
| Library | Problem it solves |
|---|---|
| insurance-causal | Double machine learning to deconfound rating factors where channel and behaviour bias standard GLM coefficients |
Uncertainty quantification
| Library | Problem it solves |
|---|---|
| insurance-conformal | Distribution-free prediction intervals with finite-sample coverage guarantees; Solvency II SCR bounds |
| insurance-distributional-glm | GAMLSS for Python: model mean, dispersion, shape, and zero-inflation as functions of covariates |
Smoothing and experience rating
| Library | Problem it solves |
|---|---|
| insurance-whittaker | Whittaker-Henderson 1D/2D smoothing with REML lambda selection and Bayesian credible intervals |
| insurance-credibility | Bühlmann-Straub credibility in Python with mixed-model equivalence — caps thin segments, stabilises NCD factors |
Telematics
| Library | Problem it solves |
|---|---|
| insurance-telematics | HMM driving state classification from raw 1Hz GPS/accelerometer data to GLM-compatible risk scores |
Advanced modelling
| Library | Problem it solves |
|---|---|
| insurance-frequency-severity | Sarmanov copula joint frequency-severity with analytical premium correction — tests the independence assumption every model makes |
| insurance-gam | EBM and Neural Additive Model: transparency of a GLM, predictive power of a neural network |
34 libraries in total, covering the full pricing workflow from data validation through to deployment and monitoring. See burning-cost.github.io/tools for the complete list.