Starling cuts marketplace fraud exposure with Gemini-powered Scam Intelligence tool

Digital neo-banks like Starling operate in an environment where customers increasingly transact on peer-to-peer marketplaces — platforms such as Facebook Marketplace where fraud is rampant and seller verification is minimal. Starling customers were routinely exposed to elaborate scams: fraudulent listings engineered to extract payments before buyers could assess legitimacy. With no automated mechanism to evaluate ad authenticity at the point of payment, the bank relied entirely on customer vigilance — a gap that translated directly into fraud losses and eroded account holder trust. Starling needed a scalable intervention that could assess risk proactively at the moment of decision, and educate customers on warning signs rather than simply blocking transactions after the fact.

Starling built its Scam Intelligence tool on Gemini's multimodal large language model capabilities, deployed through Google Cloud's Vertex AI infrastructure. The approach centers on image-based ad analysis: customers submit a photo of a marketplace listing and Gemini processes the image alongside contextual cues, flagging red flags such as suspiciously low prices, seller pressure tactics, or other hallmarks of fraudulent listings. The tool returns a risk assessment that helps customers decide whether to proceed — simultaneously educating them on warning signs for future transactions. The Gemini prompt is continuously evaluated and managed through Vertex AI Pipelines, ensuring fraud intelligence stays current as scam patterns evolve. Model Armor guardrails constrain the tool strictly to its intended scope, a non-negotiable requirement in a regulated banking environment. Development used Vertex AI Workbench with fully automated ML training pipelines, eliminating manual intervention from the build cycle.

The first phase of Scam Intelligence reached consumer testing in just four weeks — a timeline made possible by codifying the entire model training pipeline from day one and letting training code run without manual intervention. The business impact was immediate:

• 300% increase in the rate at which customers cancel marketplace payments after reviewing Scam Intelligence assessments, directly reducing fraud exposure
• 4-week build cycle from development to first consumer testing phase, demonstrating the delivery velocity achievable with Vertex AI Workbench and automated ML pipelines

Beyond the headline numbers, the tool shifted Starling's fraud prevention posture from reactive to proactive — placing risk assessment in the customer's hands at the moment of decision.

• Gemini's multimodal capability enables image-based ad analysis — a fraud-prevention approach impossible with text-only models and directly relevant to peer-to-peer marketplace scams.
• Codifying the full model training pipeline upfront, not as a post-launch retrofit, was the primary driver of the four-week delivery timeline.
• Model Armor guardrails are essential when deploying generative AI in regulated financial services — they define the boundary between a useful customer tool and an institutional liability.
• Educating customers on warning signs rather than silently blocking transactions builds durable fraud resistance that compounds beyond the tool itself.