What question did this study set out to answer?

This study aims to develop an integrated machine learning framework for accurately predicting insurance claim amounts and classifying fraud risk.

April 25, 2026International Journal Of Informative and Futuristic ResearchOpen Access

An Integrated Random Forest-Based Framework for Insurance Claim Amount Regression and Fraud Risk Classification in Imbalanced Datasets

View Full Paper

Ask AI

Bookmark

This study aims to develop an integrated machine learning framework for accurately predicting insurance claim amounts and classifying fraud risk.
Created a synthetic dataset of 15,000 insurance claims across 19 attributes.
Employed Random Forest models for regression (claim amounts) and classification (fraud detection) with feature normalization.
Utilized an 80/20 stratified holdout split for model training and evaluation.
Regression model achieved a Mean Absolute Error below INR 15,000 and R-squared above 0.70.
Classification model delivered accuracy exceeding 0.80 with fraud recall above 0.74 and F1-Score above 0.76, outperforming logistic regression.
Prediction outputs contained four business metrics and were stored in a MySQL database for analysis.

No takes yet. Share an insight, caveat, or question.

Randomized trial demonstrates improved claim prediction and fraud classification in insurance datasets, suggesting enhanced financial security.

Basha et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial demonstrates improved claim prediction and fraud classification in insurance datasets, suggesting enhanced financial security.