METHOD AND SYSTEM FOR AUTOMATICALLY TRAINING MACHINE LEARNING MODEL

A method and a system for automatically training a machine learning model. The method comprises: obtaining a data set comprising multiple data records (S310); determining a feature engineering strategy for the data set by means of meta-learning (S320); generating features related to each data record...

Full description

Saved in:
Bibliographic Details
Main Authors CAO, Rui, LUO, Yuanfei, TU, Weiwei
Format Patent
LanguageEnglish
French
German
Published 09.11.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:A method and a system for automatically training a machine learning model. The method comprises: obtaining a data set comprising multiple data records (S310); determining a feature engineering strategy for the data set by means of meta-learning (S320); generating features related to each data record in the data set using the determined feature engineering strategy (S330); constructing machine learning samples on the basis of at least the generated features (S340); and using the constructed machine learning samples to train a machine learning model on the basis of the automatically obtained hyper-parameter values (S350).
Bibliography:Application Number: EP20200823331