Hyper-parameter determination method, apparatus and device

Abstract

Embodiments of the invention provide a hyper-parameter determination method, apparatus and device. The method comprises the steps of obtaining a first preset number of hyper-parameter sets; obtaininga first data set and a second data set, and by taking values in each hyper-parameter set as values of hyper-parameters in a preset classification algorithm, performing classification processing on data in the first data set and the second data set, thereby obtaining a first confidence degree and a second confidence degree corresponding to each hyper-parameter set; calculating a weight value of each hyper-parameter set according to the confidence degree corresponding to each hyper-parameter set; according to the obtained values in each hyper-parameter set and weight value of each hyper-parameter set, estimating a value of each hyper-parameter by utilizing a Bayesian optimization algorithm, obtaining new hyper-parameter sets and accumulating the number of the hyper-parameter sets; and takingthe values in the hyper-parameter set with the maximum weight value as the values of the hyper-parameters in the preset classification algorithm when the accumulated number of the hyper-parameter sets reaches a second preset number. By applying the method provided by the embodiment of the invention, the hyper-parameter determination efficiency can be improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a hyperparameter determination method, device, and equipment. Background technique [0002] Classification algorithms are more and more widely used in the field of intelligent recognition. Among them, the mainstream classification algorithms include: decision tree, random forest, gradient boosting decision tree (GBDT) and xgboost (Extreme Gradient Boosting), etc. Programmers can build a classification model through classification algorithms, and then use the classification model to quickly and accurately classify data, and the classified data can be used as the basis for other applications. For example, classify user data through a classification model, extract loan data, repayment data, etc. used to represent user credit, and then judge whether the user is a user at risk of default based on the extracted data. [0003] However, when adjusting the hyperparameters conta...

AI Technical Summary

Problems solved by technology

[0003] However, when adjusting the hyperparameters contained in the classification algorithm during the construction of the classification model, it usually requires programmers to make repeated adjustments based on experience, so that the constructed classification model can obtain ideal classification results when classifying the data. This adjustment method not only It is very energy-intensive for programmers, and it is cumbersome and inefficient

Images