Shift Technology's AI uncovered reused photo fraud in multiple insurance claims. Our solution detected similar photos across different claims and identified a common fraudulent broker, enabling insurers to stop payouts quickly and prove fraud with desktop investigations, saving valuable resources.
This video is part of a series of interesting cases, featuring several of our insurance-focused team of data scientists.
If you don't see the video above click the button below to adjust your cookie settings
Manage CookiesAI for Insurance in Action: Uncovering Reused Photo Fraud
"The case I want to share with you involved the reuse of a photo. We have an insured individual who submitted a photo showing damage to refrigerated goods, claiming it was caused by storms. He is unsure of the exact date of the storms. The photo shows his refrigerator, specifically the freezer, was damaged. And he provided these images as evidence that his food was indeed spoiled.
Our system detected that this photo had been used in three different previous claims. These claims involved different insured individuals, different risks, and different homes. Detecting such cases manually would be extremely difficult for a claims handler. The same claims handler would need to process all related claims and possess an excellent memory to recognize the repeated photo. Our solution identifies these cases thanks to the similarity score between the photos, indicating that they are indeed very similar. An alert is then generated.
Moreover, our solution detected another link between the three claims: the same agent or intermediary was involved in all of them. Typically, these kinds of cases are processed and paid out quickly. Our solution enables the detection and halting of these fraudulent claims before payment, allowing us to prove the fraud rapidly. A simple desktop investigation can confirm the fraud and stop the broker's fraudulent operations."
