Sony Corporation

Sony Group Corporation

Sony Interactive Entertainment Inc.

Cristian Traum

Conor Aylward

Olivier Elshocht

Erbin Lim

Barbara Jochems

Ales Novak

Bart Vandezande

Hugo Embrechts

Francesco Cartella

Gert Ceulemans

Orlando Anunciacao

Gabriel Armelin

Igor Bondarenko

Lee Kirsten Gould

Johan Duyshaver

Alexei Karpov

Romain Henneton

Examples relate to a method, a computer program and a system for enabling a verification of a result of a computation obtained from a third party. The method comprises providing a model on a distributed ledger, the model representing the computation used by the third party. The method comprises providing access to the model for one or more users, to enable the users to verify the result of the computation.

Method, computer program and system for enabling a verification of a result of a computation

Training a machine learning model includes selecting a subset of training transactions from a plurality of training transactions to be used for classifying transactions as either fraudulent or genuine, and classifying transactions as either fraudulent or genuine. Additionally, selecting the subset of training transactions includes clustering the plurality of training transactions into a plurality of clusters based on a similarity measure. Each training transaction includes an indication whether the training transaction is fraudulent or genuine. Further, selecting the subset of training transactions includes selecting a first proportion of the training transactions of a cluster of training transactions for the subset of training transactions if the cluster comprises at least one fraudulent training transaction, and selecting a second proportion of the training transactions of a cluster of training transactions for the subset of training transactions if the cluster is free of fraudulent training transactions.

Method, apparatus and computer program for selecting a subset of training transactions from a plurality of training transactions

The present disclosure relates to a concept of fraud handling. A data transaction request is received via a data network from at least one user account. The data transaction request is analyzed based on predefined fraud detection rules to generate a fraud score associated with the at least one user account. The at least one user account is classified as fraudulent account if the associated fraud score exceeds a predefined fraud likelihood threshold. Data transactions associated with a classified fraudulent account via the data network are pseudo-randomly permitted or blocked.

Methods and apparatuses for fraud handling

The present disclosure relates to a concept of fraud handling. A data transaction request is received via a data network from at least one user account. The data transaction request is analyzed based on predefined fraud detection rules to generate a fraud score associated with the at least one user account. The at least one user account is classified as fraudulent account if the associated fraud score exceeds a predefined fraud likelihood threshold. Data transactions associated with a classified fraudulent account via the data network are done by purposely deteriorating the data transactions associated with the classified fraudulent account in comparison to data transactions associated with a classified non-fraudulent account.

A method comprising partitioning a space of user requests into subsets, and determining a risk score for a user request based on the evolution of the number of user requests in the subset of user requests to which this user request belongs.

Method, apparatus and system for calculating a risk score of a user request by a user on a web application

Growing community of inventors

Stuttgart, Germany

Cristian Traum