Machine learning model training method and device

Abstract

The invention discloses a machine learning model training method and device. The method comprises the following steps: on the basis of initialized first weight and second weight of each sample in a training set, and with features of each sample as granularity, training a machine learning model; on the basis of prediction loss of each sample in the training set, determining a first sample set, where corresponding target variables are predicated inaccurately, and a second sample set, where corresponding target variables are predicated accurately; on the basis of the prediction loss of each sample in the first sample set and the corresponding first weight, determining overall prediction loss of the first sample set; on the basis of the overall prediction loss of the first sample set, improving the first weight and the second weight of each sample in the first sample set; and inputting the updated second weight of each sample in the training set and features of each sample and the target variables into the machine learning model, and with the features of each sample as granularity, training the machine learning model. Through the machine learning model training method and device, prediction accuracy and training efficiency of the machine learning model can be improved.

Description

technical field [0001] The present invention relates to machine learning technology in the computer field, in particular to a machine learning model training method and device. Background technique [0002] Machine learning (ML, Machine Learning) is a multi-field interdisciplinary technology, which is constantly being applied in the actual industrial field. [0003] The supervised method is a scheme currently used to train machine learning models, based on the sample features in the training set (such as the title content of the email, the user's credit data, etc.) and the classification results (also known as target variables, such as the user's credit rating ) to train the machine learning model, so that the machine learning model has the ability to predict the classification of samples outside the training set. [0004] For example, use machine learning models to distinguish high-quality customers from non-high-quality customers in the credit investigation business, dist...

AI Technical Summary

Problems solved by technology

[0005] At present, in the process of machine learning models including multiple classifiers based on supervised training, such as XGBoost (Extreme Gradient Boosting) model, there is a problem that the classification of some samples in the training set is always difficult to predict.

[0006] For example, when training a machine learning model for classifying high-quality customers from non-high-quality

Images