HOMEY: Heuristic Object Masking with Enhanced YOLO for Property Insurance Risk Detection

TL;DR

HOMEY is a novel computer vision framework that enhances YOLO with heuristic masking and custom loss to accurately detect property risks, supporting scalable insurance risk assessment.

Contribution

It introduces heuristic object masking and a risk-aware loss function to improve detection of property risks with YOLO, tailored for insurance applications.

Findings

Achieves higher detection accuracy than baseline YOLO models

Maintains fast inference suitable for real-time applications

Enables interpretable risk analysis for insurance workflows

Abstract

Automated property risk detection is a high-impact yet underexplored frontier in computer vision with direct implications for real estate, underwriting, and insurance operations. We introduce HOMEY (Heuristic Object Masking with Enhanced YOLO), a novel detection framework that combines YOLO with a domain-specific masking mechanism and a custom-designed loss function. HOMEY is trained to detect 17 risk-related property classes, including structural damages (e.g., cracked foundations, roof issues), maintenance neglect (e.g., dead yards, overgrown bushes), and liability hazards (e.g., falling gutters, garbage, hazard signs). Our approach introduces heuristic object masking to amplify weak signals in cluttered backgrounds and risk-aware loss calibration to balance class skew and severity weighting. Experiments on real-world property imagery demonstrate that HOMEY achieves superior detection accuracy and reliability compared to baseline YOLO models, while retaining fast inference. Beyond detection, HOMEY enables interpretable and cost-efficient risk analysis, laying the foundation for scalable AI-driven property insurance workflows.