A model was built to predict the total insurance claim amount payable by the insurance company using machine learning techniques such as regression in python.

This is a note book of exploratory data analysis on cross selling of health insurance customers on vehicle insurance product and using machine learning to predict whether a customer is interested or not in vehicle insurancen

A multi-modal deep learning fusion system for vehicle insurance fraud detection. Combines tabular, temporal, and graph embeddings through a DNN classifier with PR-AUC optimization, threshold tuning for business cost minimization, and optional focal-loss retraining to handle class imbalance.

AI-Visionary 車両画像判定AI

ClaimScope is a vehicle insurance claims portfolio intelligence platform that identifies warranty concentration, geographic imbalance, and anomalous claims using explainable analytics. Built on DuckDB and IsolationForest, it turns raw claims data into actionable triage signals — no actuarial black boxes, no LLM fabrication.

A company has customer data that contains 8 columns of customer details and another table having name customer_policy data contains the policy details of the customer. The company Intends to offer some discounts in premium for certain customers.

Blockchain-enabled predictive maintenance framework for dynamic vehicle insurance premiums using XGBoost, Ethereum, Chainlink oracles, and smart contracts.

A complete Vehicle Insurance Management System built to streamline policy management, claims tracking, and customer information using efficient and scalable methods.

To predict whether the Health insurance policy-holders (customers) from past year will also be interested in Vehicle Insurance provided by the company.

Vehicle Insurance Claim Fraud Detection using decision-trees, random-forest and logistic regression.

This is a project to demonstrate a robust MLOps pipeline to manage the lifecycle of a "vehicle insurance prediction" machine learning model

Vehicle Insurance Fraud Detection using Machine Learning to classify insurance claims as fraudulent or genuine. The project involves data preprocessing, exploratory data analysis, handling class imbalance, and building classification models like Logistic Regression, Decision Tree, and Random Forest to identify fraud patterns and improve detection.

AWS‑powered end‑to‑end MLOps pipeline for vehicle insurance data ingestion, training & deployment

Comprehensive cross-border vehicle insurance portal for travelers driving from Malaysia to Thailand. Compare plans, view border crossing guides, and get expert assistance for Compulsory (TPBI) and Voluntary insurance.