公开(公告)号：US11687769B2

公开(公告)日：2023-06-27

申请号：US15639580

申请日：2017-06-30

Applicant: PayPal, Inc.

Inventor： David Tolpin ,  Benjamin Hillel Myara ,  Michael Dymshits

IPC: G06N3/08 ,  G06N20/00 ,  G06N3/082 ,  G06N3/045 ,  G06Q30/06 ,  G06F16/35

CPC classification number: G06N3/08 ,  G06F16/35 ,  G06N3/045 ,  G06N3/082 ,  G06N20/00 ,  G06Q30/06

Abstract: Machine learning techniques can be used to train a classifier, in some embodiments, to accurately detect similarities between different records of user activity for a same user. When more recent data is received, newer data can be analyzed by selectively removing particular sub-groups of data to see if there is any particular data that accounts for a large difference (e.g. when run through a classifier that has been trained to produce similar results for known activity data from a same user). If a sub-group of data is identified as being significantly different from other user data, this may indicate an account breach. Advanced machine learning techniques described herein may be applicable to a variety of different environments.

公开(公告)号：US20190199741A1

公开(公告)日：2019-06-27

申请号：US15852331

申请日：2017-12-22

Applicant: PAYPAL, INC.

Inventor： Benjamin Hillel Myara ,  David Tolpin

IPC: H04L29/06 ,  H04L29/08 ,  G06F17/27

CPC classification number: H04L63/1425 ,  G06F17/2785 ,  H04L67/14

Abstract: Methods and systems for creating and analyzing low-dimensional representation of webpage sequences are described. Network traffic history data associated with a particular website is retrieved and a word embedding algorithm is applied to the network traffic history data to produce a low dimensional embedding. A prediction model is created based on the low-dimensional embedding. Browsing activity on the particular website is monitored. A set of sessions in the current browsing activity is flagged based on a result of applying the prediction model to the monitored browsing activity.

公开(公告)号：US20190130254A1

公开(公告)日：2019-05-02

申请号：US15794832

申请日：2017-10-26

Applicant: Paypal, Inc.

Inventor： David Tolpin ,  Amit Batzir ,  Nofar Betzalel ,  Michael Dymshits ,  Benjamin Hillel Myara ,  Liron Ben Kimon

IPC: G06N3/04 ,  G06N3/08

Abstract: Anomalies in a data set may be difficult to detect when individual items are not gross outliers from a population average. Disclosed is an anomaly detector that includes neural networks such as an auto-encoder and a discriminator. The auto-encoder and the discriminator may be trained on a training set that does not include anomalies. During training, an auto-encoder generates an internal representation from the training set, and reconstructs the training set from the internal representation. The training continues until data loss in the reconstructed training set is below a configurable threshold. The discriminator may be trained until the internal representation is constrained to a multivariable unit normal. Once trained, the auto-encoder and discriminator identify anomalies in the evaluation set. The identified anomalies in an evaluation set may be linked to transaction, security breach or population trends, but broadly, disclosed techniques can be used to identify anomalies in any suitable population.

公开(公告)号：US20180218261A1

公开(公告)日：2018-08-02

申请号：US15420613

申请日：2017-01-31

Applicant: PAYPAL, INC.

Inventor： Benjamin Hillel Myara ,  David Tolpin

IPC: G06N3/08 ,  H04W12/12 ,  H04L29/06 ,  G06N5/04 ,  G06Q20/40

CPC classification number: G06Q20/4016 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/084 ,  G06Q20/00 ,  H04L63/1441 ,  H04W12/00505 ,  H04W12/00508 ,  H04W12/12

Abstract: A system for predicting that a user session will be fraudulent. The system can analyze an incomplete session and determine the likelihood that the session is fraudulent or not by generating completed sessions based on the incomplete session.