Repository of GEMAct source code. Enjoy!

GLM, Neural Network and Gradient Boosting for Insurance Pricing, Part 1: Claim Frequency

XGBoost Regressor to predict healthcare expenses based on features such as age, BMI, smoking, etc.

Claw🦞 agentic driven InsurTech🛡🤖AI-driven infrastructure that programmatically underwrites, covers risk, and processes claims/fraud with precise, algorithmic protection.

InsureSight is an intelligent insurance pricing engine that leverages ML to forecast premiums using demographics, medical history, and lifestyle factors. Delivers instant, data-driven cost predictions via an intuitive Streamlit interface.

Actuarial tail risk quantile/expectile regression for insurance pricing - TVaR, large loss loading, ILF curves, CatBoost

Data visualization about smoking impact on insurance annual charges

Constrained portfolio rate optimisation for insurance pricing — SLSQP, FCA ENBP, efficient frontier, shadow prices, JSON audit trail

Model governance for insurance pricing — PRA SS1/23 validation reports, model risk management, risk tier scoring

GLM tooling for insurance pricing — nested GLM embeddings, R2VF factor level clustering, territory banding, SKATER

AssuredLife is a modern, full-stack web application designed to streamline the process of purchasing and managing life insurance policies. It provides a secure, responsive, and role-based platform for customers, agents, and administrators.

Insurance Premium Optimization (End-to-end ML Ops project)

This is the backend server for AssuredLife - a modern life insurance management platform. It is a role-based full-stack web application built with the MERN stack. It provides a secure and robust REST API to support the client-side application.

End-to-end insurance pricing pipeline: CatBoost frequency model, SHAP relativities, fairness audit, monitoring, and conformal intervals on a single synthetic UK motor dataset

GAMLSS for insurance pricing in Python — model variance, shape, and tail parameters as functions of covariates

A curated list of awesome responsible machine learning resources.

Free 12-module course: Modern Insurance Pricing with Python and Databricks. GLMs, GBMs, SHAP relativities, conformal prediction, Bayesian credibility, rate optimisation, causal demand modelling, monitoring, spatial territory rating.

Density ratio correction for insurance pricing book shifts — CatBoost/RuLSIF/KLIEP, LR-QR conformal, FCA SUP 15.3 diagnostics

Model drift detection for insurance pricing — exposure-weighted PSI/CSI, A/E ratios, Gini drift z-test

To view the report and the semantic model of this repository click the link below