Paypal, Inc.

Ying Lin

Jiaqi Zhang

Huagang Yin

Yu Zhang

Pengshan Zhang

Haoran Zhang

Junshi Guo

Zohar Li Marad

Delin Liu

Alon Wiener

There are provided systems and methods for pairwise graph querying, merging, and computing for account linking. A service provider may provide an account graph system to identify pairwise similarities between different accounts based on shared data that may be identified through one or more linking characteristics. When providing pairwise graph similarities, a service provider may receive a query identifying two or more accounts and/or an account with a parameter for graph exploration and querying. The service provider may utilize connection, link, or relationship graphs, queried and generated using a graph database, to determine pairwise similarities between the designated seed account and one or more selected accounts. The graph may include vertices for different queried data points and edges connecting such queries, where directionality of the edges or other vectors may be used to identify links or hops between accounts for data querying and exploration.

Pair-wise graph querying, merging, and computing for account linking

Computer system security can be improved through the use of whitelists and blacklists based on Bloom filters in the context of real-time data and electronic actions. A transaction may use a specific asset. A first search of the specific asset can be conducted in a Bloom filter whitelist comprising first assets classified as having a first status. The first search may return a plurality of first binary results corresponding to different hash functions performed the first assets. A second search of the specific asset can be conducted in a Bloom filter blacklist comprising second assets classified as having a second status different from the first status. The second search can return a plurality of second binary results corresponding to different hash function performed on the second assets, and the specific asset can be determined to be good or bad based on values of the first and second binary results.

Bloom filter whitelist and blacklist operations

Various techniques are disclosed for providing dynamic, real-time pattern detection and linking between newly created user accounts and existing user accounts. Certain solutions include assessing matches of a new user account to nodes in a graphical representation of a machine learning algorithm based on predefined patterns in the properties of the new user account. The nodes in the graphical representation may each have different predefined patterns that have been determined based on patterns in previous information for user accounts, which can also be updated in real-time as needed. Accordingly, when a new user account is matched (e.g., assigned) to a node that has accounts with known issues associated with the node, the new user account may be flagged for increased scrutiny or other solutions.

System and method for pattern detection in user accounts through fuzzy pattern matching

Systems and methods for processing machine learning attributes are disclosed. An example method includes: identifying a user transaction associated with a set of transaction attributes and a first transaction status; selecting, based on a risk evaluation model, a first plurality of transaction attributes from the set of transaction attributes; modifying a first value of a first transaction attribute in the first plurality of transaction attributes to produce a first modified plurality of transaction attributes; determining, based on the risk evaluation model, that the first modified plurality of transaction attributes identify a second transaction status different from the first transaction status; and in response to the determining, identifying the first transaction attribute as a risk attribute associated with the user transaction.

Growing community of inventors

Shanghai, China

Ying Lin