Executive Summary

Retailers collectively lose billions to shrink each year, and shoplifting—both opportunistic and organized—remains a primary driver; loss-prevention teams at roughly 120,000 enterprise locations are already budgeting for analytics and software to reduce those losses. Current computer-vision approaches are hampered by severe data scarcity for rare events, inconsistent labeling across sites, and privacy/legal barriers that make it hard to build robust, production-grade detectors. You could build a curated, open video dataset of annotated shoplifting and loss-related incidents paired with a synthetic-augmentation pipeline that generates diverse, rare-event variants (different camera angles, clothing, occlusion, group dynamics) plus standardized labels and evaluation suites. Package this with baseline on-device models, SDKs for inference, and a subscription/licensing model so retailers, system integrators, and researchers can train, benchmark, and deploy solutions faster. The timing is attractive: about 120,000 enterprise retailers represent a ~$12B addressable market at roughly $100k ACV per customer, edge compute costs have dropped enough to enable low-latency on-device inference, and recent advances in transformers, self‑supervised learning, and synthetic-data tooling materially lower the cost to create diverse, realistic training examples. To stand out, prioritize high-quality curation, rigorous anonymization and compliance workflows, realistic physics- and behavior-based synthesis, and an independent benchmark that reduces vendor lock-in; these make the dataset practical and defensible. Be honest about the challenges: obtaining consented, legally compliant real-world footage, dealing with domain shift between store formats and cameras, and competing with established security vendors who may develop or acquire similar assets.

Market Opportunity

Retail shrink from shoplifting — curated open dataset + synthetic augmentation targets a $12.0B = 120,000 enterprise retailers x $100k ACV (loss-prevention software, analytics & services) total addressable market with medium saturation and a year-over-year growth rate of 18% — global retail video analytics & AI market CAGR estimates.

Key trends driving demand: Ubiquitous CCTV & cheaper edge compute -- more deployment points for on-device inference and faster ROI for analytics.; SOTA vision models (transformers, self-supervised learning) -- improved capability on limited or noisy video inputs.; Synthetic-data tooling -- dramatically reduces the cost and time to create diverse, rare-event training examples.; Privacy regulation & consumer scrutiny -- demand for anonymized, compliant datasets and federated learning..

Key competitors include BriefCam (now Canon/Canon Inc.), Avigilon (Motorola Solutions), Veesion, Datagen, Academic / Open Datasets (COCO, MOTChallenge, DukeMTMC, PETS).

Sign in to access

Retail shrink from shoplifting — curated open dataset + synthetic augmentation

Executive Summary

Market Validation

Market Opportunity

More in Data & Analytics

Automated reporting for data/ML pipelines that generates model-aware operational reports

Stop full-table scans on lakehouses with spatial + time indexing

SaaS founders can't explain churn — automated root‑cause analysis & recovery

SEC JS-pagination blocks comment scraping — build headless crawler + NLP index

Restore Excel & human-in-loop workflows for modern BI/AI pipelines

Measure real process bottlenecks first — then automate with robots