Ensemble learning method based on heuristic sampling

Abstract

An ensemble learning method for heuristic sampling is suitable for classification of an unbalanced data set, and comprises the following steps: dividing the data set into a second category according to distribution characteristics of all samples in the data set in a characteristic space; respectively setting different hardness weights according to the second category of each sample, and calculating the selection probability of each sample in combination with the unbalanced weight; and resampling the data set according to the selected probability of each sample, and performing integrated training on the resampled data set to obtain a final classification result. According to the method, emphasized resampling is carried out on the basis of the intrinsic characteristics of the sample, so thatthe sampling quality of the unbalanced data set is improved, and the classification effect of an existing ensemble learning method on the unbalanced data set is improved.

Description

technical field [0001] The invention relates to the technical fields of data mining and machine learning, in particular to an integrated learning method based on heuristic sampling. Background technique [0002] In recent years, data mining and machine learning models have been widely used in various fields of life. Among them, the classification problem is one of the important tasks faced in the field of machine learning. The construction of traditional classification models is usually based on the following assumptions: the number of samples in each category in the data set is balanced. However, in many real-world applications, this assumption is not valid, that is, there is a phenomenon of category imbalance in the data set. Such as: transaction fraud detection, network intrusion detection, biological gene detection, spam filtering, etc., the data are not balanced. And when this unbalanced phenomenon occurs, the classifier's recognition accuracy for a small number of c...

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of the above existing integration methods when dealing with unbalanced data sets, the purpose of the present invention is to provide an integrated learning method for heuristic sampling, which is used to solve the problem of the sampling quality of the existing integrated learning methods for unbalanced data sets. High, and the classification effect of the integrated learning method on the data set is reduced due to the imbalance of the pre-sampled data

Images