Predict Harmful Gambling Behavior

Business Problem

Gambling regulators require remote gambling operators to make active use of the wealth of customer information at their disposal to identify customers who are likely to exhibit harmful gambling behavior. In addition to this identification process, it must be demonstrated that the operator has attempted to intervene early and prevent harm to the customer. See UK examples in the References section.

If a regulator identifies failures to meet these requirements, compliance and enforcement action can be taken (see example here). Gambling companies who are concerned about customer welfare, and want to avoid hefty fines, are beginning to apply sophisticated machine learning approaches to this business problem.

Intelligent Solution

AI helps remote gambling operators identify patterns of harmful gambling behavior. AI models are fast and scalable, allowing the entire customer base to be tracked in near real-time to ensure signals are picked up early. The Customer Interaction team, which would be unable to assess the entire customer base manually, can focus on the highest risk customers and intervene appropriately. For example, they can schedule a phone call, restrict bet amounts, or freeze an account entirely.

DataRobot Automated Feature Discovery can be leveraged to aggregate thousands of customer events/transactions and find patterns that suggest a customer is at risk. DataRobot Anomaly Detection can also be used to identify new patterns of unusual behavior.