Amazon Technologies, Inc.

Matthew Butler

Christos Faloutsos

Mina Loghavi

Ching-Heng Chiu

Yi Fan

Charles Martin Babington

Techniques are disclosed for generating a ranked list of content for a user account of a service provider. A server device can determine that a first user account of a service provider is linked with a second user account of the service provider. The server device can then determine whether the first user account has been registered with the service provider a time period less than a threshold time. In response, the server device can determine interaction information associated with the second user account and generate, using a ranking model taking the interaction information as an input, a ranked list of content offered by the service provider. The server device can then cause the user device to present content at a graphical user interface of the user device according to the ranked list of content.

Cross-user account management on user devices

Devices and techniques are generally described for fraud detection. A machine learning model is used to determine a first fraud risk score for a first transaction. The machine learning model includes a first set of weights. A first covariance matrix is determined for the machine learning model based at least in part on the first fraud risk score. A second set of weights for the machine learning model is determined. The second set of weights is determined based on the first set of weights and the first covariance matrix. In various examples, the machine learning model with the second set of weights is used to determine a second fraud risk score for a second transaction. A fraud decision surface is determined and the second fraud risk score is compared to the fraud decision surface. Data indicating that the second transaction is fraudulent is sent to a computing device.

Growing community of inventors

Seattle, WA, United States of America

Matthew Butler