Adapted tree boosting for Transfer Learning
This work provides a domain-specific solution for improving fraud detection in online payment platforms like Alipay, but it is incremental as it applies existing transfer learning concepts to tree boosting models.
The paper tackles the problem of fraud detection in new e-commerce scenes with limited training data by adapting gradient boosting tree models from similar old scenes to the target domain, resulting in a transfer learning approach that addresses cold-start and data-sharing issues.
Secure online transaction is an essential task for e-commerce platforms. Alipay, one of the world's leading cashless payment platform, provides the payment service to both merchants and individual customers. The fraud detection models are built to protect the customers, but stronger demands are raised by the new scenes, which are lacking in training data and labels. The proposed model makes a difference by utilizing the data under similar old scenes and the data under a new scene is treated as the target domain to be promoted. Inspired by this real case in Alipay, we view the problem as a transfer learning problem and design a set of revise strategies to transfer the source domain models to the target domain under the framework of gradient boosting tree models. This work provides an option for the cold-starting and data-sharing problems.