Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022011181 - AUTO-TUNING OF RULE WEIGHTS IN PROFILES

Publication Number WO/2022/011181
Publication Date 13.01.2022
International Application No. PCT/US2021/040950
International Filing Date 08.07.2021
IPC
G06N 5/02 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
02Knowledge representation
CPC
G06F 21/316
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
21Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
30Authentication, i.e. establishing the identity or authorisation of security principals
31User authentication
316by observing the pattern of computer usage, e.g. typical user behaviour
G06F 21/604
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
21Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
60Protecting data
604Tools and structures for managing or administering access control systems
G06F 21/6218
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
21Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
60Protecting data
62Protecting access to data via a platform, e.g. using keys or access control rules
6218to a system of files or objects, e.g. local or distributed file system or database
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 20/20
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
20Ensemble learning
G06N 3/0427
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0427in combination with an expert system
Applicants
  • VISA INTERNATIONAL SERVICE ASSOCIATION [US]/[US]
Inventors
  • BODING, Benjamin Scott
  • WEN, Ge
Agents
  • RACZKOWSKI, David B.
  • JEWIK, Patrick R.
  • DORAN, Neslihan I. Doran-Civan
  • MILLER, Patrick B.
  • UY, Ruthleen
Priority Data
16/926,53510.07.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) AUTO-TUNING OF RULE WEIGHTS IN PROFILES
(FR) AUTO-RÉGLAGE DE POIDS DE RÈGLE DANS DES PROFILS
Abstract
(EN) Disclosed is a system to optimize rule weights for classifying access requests so as to manage rates of false positives and false negative classifications. A rules suggestion engine may suggest a profile of classification rules to a merchant for access requests. The system can optimize weights for the profile of rules using a cost function based on a training set of historical access requests, for example using stepwise regression or machine learning (ML). The system can compute a profile score based on the optimized weights, for example by summing the weights. The system statistically analyzes the profile score using classification thresholds and the historical access requests. The system can perform receiver operating characteristic (ROC) analysis for various threshold values, enabling a user to select a suitable threshold. The system can further optimize by adding or removing rules from the profile of rules.
(FR) L'invention concerne un système pour optimiser des poids de règle pour classer des demandes d'accès de façon à gérer des taux de classements en faux positifs et en faux négatifs. Un moteur de suggestion de règles peut suggérer un profil de règles de classement à un commerçant pour des demandes d'accès. Le système peut optimiser des poids pour le profil de règles à l'aide d'une fonction de coût basée sur un ensemble d'apprentissage de demandes d'accès historiques, par exemple à l'aide d'une régression pas à pas ou d'un apprentissage machine (ML). Le système peut calculer un score de profil sur la base des poids optimisés, par exemple par addition des poids. Le système analyse statistiquement le score de profil à l'aide de seuils de classement et des demandes d'accès historiques. Le système peut effectuer une analyse de caractéristique de fonctionnement de récepteur (ROC) pour diverses valeurs de seuil, ce qui permet à un utilisateur de sélectionner un seuil approprié. Le système peut en outre optimiser par ajout ou retrait de règles dans le profil de règles.
Related patent documents
Latest bibliographic data on file with the International Bureau