Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020111376 - MACHINE LEARNING-BASED DEFAULT PREDICTION DEVICE AND METHOD

Publication Number WO/2020/111376
Publication Date 04.06.2020
International Application No. PCT/KR2018/016965
International Filing Date 31.12.2018
IPC
G06Q 40/02 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
40Finance; Insurance; Tax strategies; Processing of corporate or income taxes
02Banking, e.g. interest calculation, credit approval, mortgages, home banking or on-line banking
G06Q 10/04 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
04Forecasting or optimisation, e.g. linear programming, "travelling salesman problem" or "cutting stock problem"
G06Q 10/06 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
06Resources, workflows, human or project management, e.g. organising, planning, scheduling or allocating time, human or machine resources; Enterprise planning; Organisational models
G06N 20/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
CPC
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 99/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99Subject matter not provided for in other groups of this subclass
G06Q 10/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
04Forecasting or optimisation, e.g. linear programming, "travelling salesman problem" or "cutting stock problem"
G06Q 10/06
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
06Resources, workflows, human or project management, e.g. organising, planning, scheduling or allocating time, human or machine resources; Enterprise planning; Organisational models
G06Q 40/02
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
40Finance; Insurance; Tax strategies; Processing of corporate or income taxes
02Banking, e.g. interest calculation, credit approval, mortgages, home banking or on-line banking
Applicants
  • 공주대학교 산학협력단 KONGJU NATIONAL UNIVERSITY INDUSTRY-UNIVERSITY COOPERATION FOUNDATION [KR]/[KR]
Inventors
  • 최대선 CHOI, Dae Seon
  • 박소희 PARK, So Hee
Agents
  • 특허법인 아주 AJU INTERNATIONAL LAW & PATENT GROUP
Priority Data
10-2018-014851127.11.2018KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) MACHINE LEARNING-BASED DEFAULT PREDICTION DEVICE AND METHOD
(FR) DISPOSITIF ET PROCÉDÉ DE PRÉDICTION DE DÉFAUT À BASE D'APPRENTISSAGE AUTOMATIQUE
(KO) 기계 학습 기반의 채무불이행 예측 장치 및 방법
Abstract
(EN)
The present invention relates to a machine learning-based default prediction device and method, the device comprising: a data generation unit which generates time series training data by chronologically ordering a debtor’s default history information for a predetermined period in the past with respect to a current point in time; a prediction model generation unit which applies the time series training data generated by the data generation unit to a predefined machine learning model, thereby executing training of the machine learning model, and generates a default prediction model for predicting default of the debtor after the current point in time; and a default prediction unit which predicts the default of the debtor after the current point in time by inputting the time series training data generated by the data generation unit into the default prediction model generated by the prediction model generation unit.
(FR)
La présente invention concerne un dispositif et un procédé de prédiction de défaut à base d'apprentissage automatique, le dispositif comprenant : une unité de génération de données qui génère des données d'apprentissage en série chronologique par commande chronologique d'informations d'historique de défaut d'un débiteur pendant une période prédéterminée dans le passé par rapport à un moment présent ; une unité de génération de modèle de prédiction qui applique les données d'apprentissage de série chronologique générées par l'unité de génération de données à un modèle d'apprentissage machine prédéfini, ce qui permet d'exécuter l'apprentissage du modèle d'apprentissage automatique, et génère un modèle de prédiction de défaut pour prédire un défaut du débiteur après le moment présent ; et une unité de prédiction de défaut qui prédit le défaut du débiteur après le moment présent en introduisant les données d'apprentissage en série chronologique générées par l'unité de génération de données dans le modèle de prédiction par défaut généré par l'unité de génération de modèle de prédiction.
(KO)
본 발명은 기계 학습 기반의 채무불이행 예측 장치 및 방법에 관한 것으로서, 현재 시점을 기준으로 과거의 설정 기간에 대한 채무자의 채무 이력 정보를 시계열화하여 시계열 학습 데이터를 생성하는 데이터 생성부, 데이터 생성부에 의해 생성된 시계열 학습 데이터를 미리 정의된 기계 학습 모델에 적용하여 기계 학습 모델에 대한 학습을 수행함으로써 현재 시점 이후 채무자의 채무불이행을 예측하기 위한 채무불이행 예측 모델을 생성하는 예측 모델 생성부, 및 예측 모델 생성부에 의해 생성된 채무불이행 예측 모델에, 데이터 생성부에 의해 생성된 시계열 학습 데이터를 입력하여 현재 시점 이후 채무자의 채무불이행을 예측하는 채무불이행 예측부를 포함하는 것을 특징으로 한다.
Also published as
Latest bibliographic data on file with the International Bureau