AI-based fraud detection system for e-commerce
Ocado Technology, a UK division of Ocado, developed what is said to be the world's first artificial intelligent-based fraud detection system for online grocery purchases. The new system relies on an advanced machine learning algorithm using TensorFlow and the power of Google Cloud.
The system is part of the Ocado Smart Platform (OSP), an end-to-end solution designed to power all aspects of a retailer's e-commerce business.
The process is as follows:
- Customer order information is stored and analyzed using BigQuery.
- Information is then processed using Dataflow, where the data is normalized (a process whereby numerical features are re-scaled around the origin and categorical features are transformed into a sequence of integers). This reformatting is necessary for many ML algorithms, including Deep Neural Networks built using TensorFlow.
- Dataflow is also used to transfer the data from BigQuery to Datastore and cloud storage.
- Datastore provides fast data access, allowing for pre-computed features to be accessed when running real-time predictions.
- Cloud storage efficiently stores data using a file system.
- Cloud ML consumes the data from cloud storage and produces models as APIs.
- The Ocado fraud detection model, powered by TensorFlow, then reads the data from Datastore, and using the Cloud ML APIs, makes real-time predictions.