Detect whether a claim is fraudulent or not fraudulent, using Data Robot APIs.
IQ Bot 6.0 is required
Key Use Case: Fraudsters are not discriminating. They target any insurance company, large or small, that doesn't have a predictive system to catch fake claims. Without a predictive model to identify fraud, insurers have two options: 1. Review no claims and pay out on fraud OR 2. Review every claim and lose good customers at renewal time due to poor treatment and slow claims processing. With the Fraudulent Claim Detection Bot we can detect whether a claim is Fraud or Not Fraud using Data Robot APIs. In case of Fraud claim, the bot would send an email to supervisor. Otherwise, the bot would redirect the user to claim approval system.
See the Bot in Action
Download the Bot and follow the instructions to install it in your AAE Control Room.
Open the Bot to configure your username and other settings the Bot will need (see the Installation Guide or ReadMe for details.)
That's it - now the Bot is ready to get going!
Requirements and Inputs
- AAE v11.1 , IQ Bot 6.0
- DataRobot CredentialsUsernameAPI KeyDataRobot KeyProject IDModel ID 5 Variables required for training/testing/prediction modelRULE MATCHESCLAIM_TYPE_MOTOR_THEFTDISTINCT_TYPES_ON_CLAIMPOLICY_CLAIM_DAY_DIFFREGIONData Source - csv file