InsureFraudNet

InsureFraudNet — Insurance Fraud Detection

Created by Bytical AI — AI agents that run insurance operations.

Model Description

InsureFraudNet is a multi-line-of-business fraud detection system for UK insurance claims. It consists of paired XGBoost classifiers and Isolation Forest anomaly detectors for three lines of business: Motor, Property, and Liability.

New to These Hugging Face Repos?

INSUREOS is published as separate repos so each page stays focused:

• This page (InsureFraudNet) contains model artifacts and usage.
• Full training code is in piyushptiwari/insureos-models.
• Training data is in piyushptiwari/insureos-training-data.
• Beginner explanation is in LEARN.md.

Architecture

Each line of business has:

• XGBoost Classifier — Supervised gradient-boosted tree for fraud probability scoring
• Isolation Forest — Unsupervised anomaly detection for novel fraud patterns

Lines of Business

Top Fraud Indicators by LoB

Motor:

Property:

Liability:

Files

How to Use

import xgboost as xgb
import pickle
import numpy as np

# Load motor fraud model
model = xgb.XGBClassifier()
model.load_model("xgb_motor.json")

# Load isolation forest
with open("iforest_motor.pkl", "rb") as f:
    iforest = pickle.load(f)

# Example claim features
claim = np.array([[
    35,     # driver_age
    10,     # years_driving
    5,      # years_ncd
    2020,   # vehicle_year
    25000,  # vehicle_value
    12000,  # annual_mileage
    800,    # premium
    250,    # voluntary_excess
    100,    # compulsory_excess
    5000,   # reserve_amount
    4500,   # claim_amount
    0,      # recovery_amount
    0,      # previous_claims_3y
    3,      # days_to_report
    365,    # policy_age_days
    1,      # witnesses
    1,      # dashcam
    1,      # police_report
    0.9,    # claim_reserve_ratio
    5.625,  # claim_premium_ratio
    0,      # new_policy
    0,      # late_report
    4       # vehicle_age
]])

# Predict fraud probability
fraud_prob = model.predict_proba(claim)[0][1]
is_anomaly = iforest.predict(claim)[0] == -1

print(f"Fraud probability: {fraud_prob:.2%}")
print(f"Anomaly detected: {is_anomaly}")

Learn How This Model Works

New to ML or insurance AI? We wrote a plain-English guide that explains the concepts, the data, and the actual training code behind every INSUREOS model:

• Learning guide: LEARN.md
• Training code: piyushptiwari/insureos-models — this model is trained by training/fraud_model.py

Part of the INSUREOS Model Suite

This model is part of the INSUREOS — a complete AI/ML suite for insurance operations built by Bytical AI:

Citation

@misc{bytical2026insurefraudnet,
  title={InsureFraudNet: Multi-LoB Insurance Fraud Detection},
  author={Bytical AI},
  year={2026},
  url={https://huggingface.co/piyushptiwari/InsureFraudNet}
}

About Bytical AI

Bytical builds AI agents that run insurance operations — claims automation, underwriting intelligence, digital sales, and core system modernization for insurers across the UK and Europe. Microsoft AI Partner | NVIDIA | Salesforce.