Bayesian Modeling for Risk Assessment Using Dynamic Data Sources

ChangeBridge: EPO Bulletin - AI & Computing (G06N)

Published March 18th, 2026

Detected March 24th, 2026

Summary

The European Patent Office has published a patent application by Equifax Inc. detailing a method for risk assessment using Bayesian modeling with dynamic data sources. The technology aims to determine risk indicators for entities to control access to computing environments.

View original document View source feed page

What changed

This document describes a patent application (EP4708775A3) related to Bayesian modeling for risk assessment. The proposed system uses a computing device to determine a risk indicator for a target entity based on predictor variables and a Bayesian prediction model. This model is initially trained on a dataset and can be updated with additional data. The risk indicator is then transmitted to control access to interactive computing environments.

While this is a patent application and not a regulatory rule, it highlights emerging technologies in risk assessment and data analysis relevant to financial services and technology sectors. Compliance officers should be aware of such advancements, particularly concerning data privacy, cybersecurity, and the use of AI in risk management, as they may inform future regulatory expectations or industry best practices.

Source document (simplified)

← EPO Patent Bulletin

BAYESIAN MODELING FOR RISK ASSESSMENT BASED ON INTEGRATING INFORMATION FROM DYNAMIC DATA SOURCES

Search Report EP4708775A3 Kind: A3 Mar 18, 2026

Applicants

Equifax Inc.

Inventors

SHRESTHA, Prakash, BONDUGULA, Rajkumar

Abstract

Bayesian modeling can be used for risk assessment. For example, a computing device determines, using a Bayesian prediction model, a risk indicator for a target entity from predictor variables associated with the target entity. The Bayesian prediction model determines the risk indicator based on a set of parameters associated with the Bayesian prediction model. The Bayesian prediction model is generated based on an initial training dataset. The initial training dataset includes training records and predictor variables. The Bayesian prediction model can be generated by calculating the set of parameters based on the initial training dataset. The Bayesian prediction model can be updated by updating the set of parameters using an additional training dataset. The computing device transmits, to a remote computing device, the risk indicator for use in controlling access of the target entity to one or more interactive computing environments.

IPC Classifications

G06N 7/01 20230101AFI20260209BHEP G06N 5/045 20230101ALI20260209BHEP H04L 9/40 20220101ALI20260209BHEP

Designated States

AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LI, LT, LU, LV, MC, ME, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR

View original document →